Master Theses

Master Theses

Home

Master Theses

/ Current and completed projects

Ongoing

Bech Holtan J., Nudging Towards Healthy Food Choices: Exploring the Power of Attractive Images over Deep Learning-based Food Recommender Systems​, UiB, ongoing. Supervisors: Christoph Trattner.

Berget Monclair T., News Recommendation based on Incorporation of User Behaviors and News Data, UiB, ongoing. Supervisor: Mehdi Elahi, Thomas Husken.

Brunner, J. M., Cheapfake and Deepfake Media Detection Using Transformers, UiB, ongoing.

Bødtker D., Nudging Stories in News Search: The Role of Visual Attractiveness and Presentation Order Effects on Online News Consumption, UiB, ongoing. Supervisors: Alain Starke, Christoph Trattner.

Eknes-Ripl J., Using a Large Language model to present persoalised headlines in news recommender systems, UiB, ongoing. Supervisors: Alain Stark, Jia-Jeng.

Fougner., Systems in Media Domain, UiB, ongoing.

Haugbjørg Haugen, A., Political Engagement on the Twitch Streaming Platform, UiB, ongoing.

Kjartansson Mørch B., Analysis of Popularity Bias Effect in Media Recommendation, UiB, ongoing. Supervisor: Mehdi Elahi, Anastasiia Klimashevskaia.

Lium T., Context-aware Recommender, UiB, ongoing. Supervisor: Mehdi Elahi, Astrid  Tessem.

Måseidvåg P., Virtual Reality as a Collaborative technology to support decision making in remote collaboration, UiB, ongoing. Supervisor: Morten Fjeld.

Salterød Sjåvik M., Bias in Large Language Models, UiB, ongoing. Supervisor: Samia Touileb.

Sjøen V., Digital Image Forensics In The Wild: Social Media Platforms, UiB, ongoing, Bergen 2022. Supervisor: Duc Tien Dang Nguyen.

Solberg Jensen, A.,  Platformization and listener loyality in the podcast, UiB, ongoing, Bergen 2024. Supervisor: Brita Ytre-Arne.

Soltvedt Bjørndal-Riis S., Gendered named entity recognition for Amedia’s user-base analysis, UiB, ongoing. Supervisors: Lilja Øvrelid, Emiliano Guevara, and Samia Touileb.

Statle Nævdal I., Personalised News Summarization, UiB, ongoing. Supervisor: Samia Touileb, Lubos Steskal.

Stokke E., Automated Speech to Text (ASR) Quality Metric, together with TV 2, UiB, ongoing. Supervisor: Samia Touileb.

Sæter, S., Image and Video Metadata Analysis, UiB, ongoing.

Taule Nordli J., VR Memory Palaces: Can walking Improve Meorization, UiB, ongoing, Bergen 2024. Supervisor: Morten Fjeld.

Wu Chik B., News Report Adaptation for Synthetic Voice Presentation, Uib, ongoing.

Åldstedt S., Investigating and Measuring Bias in Generative Language Models, UiB, ongoing. Supervisor: Samia Touileb.

Completed

Aga Nordli A., Preventing Privacy Invasive Queries in Knowledge Graphs, UiB, Bergen, 2024. Supervisor: Andreas Lothe Opdahl.

Svellingen Lavik  B. A., Blackboard model for Semantic Analysis of News Texts, UiB, Bergen, 2024. Supervisor: Andreas Lothe Opdahl.

Abstract

This project investigates the application of a Blackboard model for rich-text annotation, focusing on the research, development, and practical use of such a model. The research method employed in this project is the construction of a blackboard model artifact specifically designed for rich-text annotation.

This model allows various annotation components to operate independently and in parallel, based on their input-output dependencies rather than a hier-archical structure. This significantly enhances the system’s flexibility. The primary aim is to create a model that supports the seamless replacement of components, ensuring future-proofing and adaptability as NLP technologies evolve. The main findings of this research demonstrate that a Blackboard model can effectively manage multiple, independent annotation components, facilitating easier updates and integration of new technologies. This flexibility addresses a critical gap in existing systems, which often struggle with scalability and adaptability. The implications of these findings suggest that adopting a Blackboard model for text annotation can lead to more resilient and maintainable NLP systems, providing a practical solution for researchers and developers working with large datasets of raw text.

Kvarv, R., A., Bruk av generative språkmodeller til å trekke ut geografisk informasjon om hendelser, UiB, Bergen 2024. Supervisor: Bjørnar Tessem.

Abstract

Denne avhandlingen fokuserer på utviklingen av programvare for å ekstrahere geospatiale data fra nyhetsartikler ved hjelp av GPT-3/4 og lagre det i en kunnskapsgraf. Målet er å løse utfordringen med å trekke ut presis informasjon om steder, og geografiske forhold fra ustrukturerte tekster. Ved å utnytte avanserte tekstanalyse- og kunstig intelligensmetoder, ønsker prosjektet å støtte journalister og bidra til informasjonsanalyse.

Erlandsen, M., Bruk av ChatGTP for klassifisering av byggesaksdokumenter: En studie i prompt engineering, UiB, Bergen 2024. Supervisor: Andreas Lothe Opdahl.

Abstract

Denne masteroppgaven undersøker hvordan ChatGPT, en avansert språkmodell utviklet av OpenAI, kan anvendes for å effektivisere nyhetsdeteksjon og -produksjon. Hovedmålet er å utvikle en pipelinje som kan klassifisere byggesaksdokumenter som nyhetsverdige eller ikke, basert på deres innhold og relevans. Det blir også presentert en løsning for forhåndsbehandling av data som del av pipelinjen.

Gjennom en iterativ designprosess ble forskjellige prompt-strategier testet, inkludert zero-shot, few-shot, chain-of-thought og tree-of-thought. Resultatene viser at avanserte prompting-teknikker klarer å klassifisere byggesaksdokumenter med høy nøyaktighet, og kan bidra til å effektivisere arbeidet til journalister.

Oppgaven konkluderer med at ChatGPT har betydelig potensial for å støtte journalistisk arbeid med en gjennomsnittlig klassifiseringsnøyaktighet på 77%, og presenterer også muligheter for videre forskning for å forbedre modellens nøyaktighet og redusere risikoen for feilinformasjon.

 

Abstract

Debatten rundt humor er like dagsaktuell som den alltid har vært, både i medier og hos publikum. Med utgangspunkt i debatten rundt humor, tar denne masteroppgaven for seg hva, hvor og hvordan komikere anser de uskrevne reglene for humor å være. De uskrevne reglene bestemmer hva som er akseptabelt å vitse om i forskjellige kulturelle og sosiale sammenhenger, noe som betegnes som humorregime. Ved hjelp av kvalitative intervjuer med kjente norske standup-komikere, som Kevin Kildal, Dag Sørås, Sigrid Bonde Tusvik, Tore Sagen og Henrik Fladseth, utforskes deres erfaringer og refleksjoner rundt hva som er tillatt innenfor humor, hvor grensene går og hvordan de uskrevne reglene håndheves.

Komikerne uttrykker at de kan vitse om alt, men det kommer frem at de likevel forholder seg til uskrevne regler. Disse reglene er formet av samfunnets normer, publikums forventninger og medienes reaksjoner. Funnene indikerer at tilhørighet til tema, opplevelse av autentisitet og publikums forventninger er sentrale faktorer som bestemmer hva de uskrevne reglene innenfor humor er.

De uskrevne reglene finner man i tidsånden man lever i, der mer spesifikt publikum, medier og internaliserte regler hos komikerne selv peker seg ut som steder man finner de uskrevne reglene. Det er også her man ser de uskrevne reglene bli håndhevd, med kanselleringskultur, publikum sine reaksjoner og mediene sin makt til å påvirke publikum og tidsånden.

Oppgaven konkluderer med at humorregimer er dynamiske og påvirkes kontinuerlig av endringer i kulturelle normer og samfunnets tidsånd. Komikere balanserer mellom å utfordre og tilpasse seg de uskrevne reglene for å kunne utøve overskridende humor for å ikke bli utsatt for negative reaksjoner fra publikum. Samtidig er det viktig å opprettholde en form for autentisitet både overfor publikum og seg selv. Debatten rundt humor som man har sett de siste årene har handlet mye om krenking og kansellering, der komikere ytrer at dette er negativt for humor som sjanger. Samtidig viser funnene i denne oppgaven at komikerne ikke er bekymret for å bli kansellert, men heller frykten for den direkte negative reaksjonen fra publikum i øyeblikket. Her er det det unge publikummet som peker seg ut som de som lettest blir krenket, og komikerne nevner spesielt studenter som en lettkrenket gruppe.

Gjennom en grundig analyse av intervjudata og teoretiske perspektiver på humor, gir oppgaven en unik innsikt i hvordan norske standup-komikere opplever og navigerer gjennom humorregimene i dagens tidsånd. Forskningen konkluderer med at komikere i Norge i dag forholder seg til humorregimer, selv om de ytrer at de kan vitse med alt.

Thorland, T., Large language models for document classification, UiB, Bergen 2024. Supervisor: Andreas Lothe Opdahl.

Abstract

This thesis is a research endeavor to explore the efficacy of large language models in conjunction with document classification.

This thesis started out as a project started together with the “Byggebot”- project, started by the PolarisMedia-group, after my thesis advisor Professor Andreas Lothe Opdahl was contacted by the project lead to see if he was interested in the idea. The original goal of this project was to see whether or not one could utilize large language models as a means of classifying “news-worthy” stories, with a focus on municipal building permit documents.

The municipality i decided on working in was Tromsø, as one of the local newspapers were working on a similar project, and were originally interested in collaborating. I eventually has issues with bad data, as there was the need to acquire them manually, and the municipal database of Tromsø had less than desirable document markings and classifications. After some trial and error, the decision on shifting the thesis to document classification itself, as this was where most of the time was spent on this project, and it seemed like an interesting angle to research. After rigorous attempts at fine-tuning models and semi-manually classified verification documents, it was unclear whether or not the models were being verified well enough because of lacking data. In the end the decision ended up being to use multiple different state-of-the-art models and compared them against each other to test the agreement between them when being tested against multiple different datasets, trying to classify each one with a similar prefixed-prompt. In the end the resulting scores seem to indicate that certain models tend to agree with each other. The argument is then that the probability of the classification being wrong when multiple models have agreed to this extent, is moderately low. The models are by no means perfect, but it seems to be a trend for certain ones to be more effective than others in some of the domains tested.

Blücher, K., A. J., IBM Watson Debater og ChatGPT som støtteverktøy for journalistikk, UiB, Bergen 2024. Supervisor: Bjørnar Tessem.

Abstract

Kunstig intelligens er mer aktuell enn noen gang, og det utforskes stadig hvordan det kan brukes til å effektivisere arbeidsprosesser. Siden journalistyrket handler mye om skriving og produsering av nyheter, artikler og tekster, er språkmodeller og generativ KI veldig relevant for denne bransjen. De siste årene har generativ KI blitt tatt mer i bruk av nyhetsmedier og journalister, og da spesielt ChatGPT. Mens ChatGPT er en språkmodell som kan hallusinere og generere falske fakta, finnes det også språkmodeller som IBM Watson Debater som er faktabaserte og dermed ikke kan hallusinere.

Denne masteroppgaven er et designforskningsprosjekt som utforsker hvordan man kan designe et støtteverktøy som kombinerer IBMs Watson Debater og OpenAI sin ChatGPT, slik at journalister kan utnytte det til tekstgenerering.

Støtteverktøyet har blitt utviklet gjennom to iterasjoner, hvor det ble gjort en formativ evaluering av første versjon, før den siste designiterasjon ble utført basert på evalueringen. Den formative evalueringen bestod av intervjuer med brukertester hvor brukere med relevant stilling og kunnskap deltok. Gjennom disse intervjuene ble det avdekket to interessante vinklinger av støtteverktøyet, og det ble derfor utviklet to forskjellige versjoner i den siste designiterasjonen.

Låg, T., Large-scale Evaluation of Context-Aware Recommender Systems in Media Domain, UiB, Bergen 2024. Supervisor: Mehdi Elahi, Lars Skjærven, Astrid Tessem.

Abstract

In the rapidly growing media streaming platforms, it has become very challenging for users to browse through the catalogue and find interesting media items to watch. As such, personalized recommender systems are a vital component of this domain. Recommender systems are digital tools that have shown to be effective in supporting users in the discovery of items tailored to their personal preferences and needs.

Traditional recommender systems build profiles of users based on their static preferences (e.g., clicks or ratings) provided for items and utilize these profiles to generate relevant recommendations for users. However, these systems fail to consider that users’ behaviors and preferences are not necessarily static properties – they change over time and depend on their contextual circumstances at the time of consumption. The most relevant items when the user was curled up on the couch watching TV in the evening might not be the most relevant items when they’re on the school bus and watching from their phone.

In this thesis I address this problem by proposing a recommender system that utilizes contextual factors such as `Time of Day’ and `Day of Week’. This methodology has been tested under two conditions: our offline evaluation setup, and online A/B testing on the largest Norwegian media streaming platform, TV 2 Play. The results show that the proposed recommender system is highly effective in generating recommendations for real users and, in the most of the cases, surpass today’s industry-standard traditional recommender systems with respect to various metrics, including Precision, Recall, F1, MAP, and Coverage.

Haaland, V. M.,  Personalized Advertisement Recommendations Using Implicit Feedback, UiB, Bergen 2024. Supervisor: Mehdi Elahi

Abstract

Online advertising is a big part of everyday life for the average internet user, and an important source of income for most mass media companies. Studies have shown that users often prefer ads that are relevant to their interests, and that users that have a positive opinion towards advertisements are less likely to use ad blockers. It is therefore beneficial for companies to personalize advertising, not only because it can increase their revenue, but also to prevent users from turning to ad blockers. Displaying personalized advertisements can be done through the use of collaborative filtering, which is a popular technique in recommender systems. In the context of advertising, collaborative filtering models can recommend an ad to a user by identifying other users with similar preferences, and then choosing an ad that they have liked. The challenge in this scenario is that users don’t explicitly express which ads they like and which they dislike. Users may instead click on ads, thereby implicitly indicating their preferences. This type of implicit feedback does however raise several challenges. One of the central challenges is how to interpret the lack of negative feedback, i.e. the events where a user has seen an ad without clicking on it. Does zero clicks mean that the user disliked the ad, is indifferent, or did they simply not notice it?

 

This master’s thesis aims to address the challenges posed by implicit feedback data, with the primary goal being to improve personalized online advertising. The research consists of two main experiments based on industry data provided by Amedia, one of the largest media companies in Norway. I propose three novel approaches to infer user preferences towards advertisements, alongside three approaches that are more traditional. By inferring user preferences, it becomes possible to employ collaborative filtering methods such as matrix factorization for generating advertisement recommendations. Three different matrix factorization models were chosen for this task. Through a comprehensive offline evaluation, a comparative analysis was conducted in order to uncover which of the scoring approaches resulted in the highest quality advertisement recommendations across several performance metrics. The findings from the experiments suggest that the proposed novel approaches were generally superior at representing user preferences compared to the more traditional approaches. Overall, the research conducted in this thesis addresses some of the challenges with using implicit feedback data for personalization, and proposes how this topic can be further explored in order to improve personalized advertising.

Hagen Risberg, K., Smidig utvikling innen mediesektoren, UiB, Bergen 2024. Supervisor: Bjørnar Tessem.

Abstract
Denne masteroppgaven utforsker anvendelsen av smidige utviklingsmetoder innenfor mediebransjen, med et særlig fokus på hvordan disse metodene bidrar til innovasjon, effektivitet og tilpasningsdyktighet i lys av bransjens raskt skiftende landskap. Gjennom en kombinasjon av teoretisk undersøkelse og empirisk forskning, inkludert case-studier, observasjoner og kvalitative intervjuer med nøkkelpersonell fra flere ledende mediebedrifter, belyser oppgaven hvordan smidige prinsipper og praksiser blir integrert i systemutvikling når det kommer til medieorganisasjoners daglige arbeid.

Oppgaven starter med en grundig gjennomgang av teoretiske perspektiver ved smidig utvikling, inkludert metodikkens historie og nøkkelelementer som Scrum, Kanban, Lean og DevOps. Denne teoretiske rammen anvendes for å forstå hvordan smidige metoder tilpasses og implementeres i mediebransjen, en sektor kjennetegnet ved sitt konstante behov for innovasjon og rask respons på forbrukertrender. Ved hjelp av forskningsmetoden som omfatter detaljerte observasjoner og dybdeintervjuer, undersøker studien spesifikke praksiser og utfordringer ved bruk av smidige metoder i mediebedrifter. Datainnsamlingen avdekker hvordan smidighet manifesterer seg gjennom sprinter, bedriftskultur, prosjektstyring, og ledergruppers rolle i defineringen av mål og prioriteringer.

Resultatene fra denne studien viser at smidige metoder har en betydelig positiv innvirkning på mediebedrifters evne til å navigere i et konkurransepreget marked. Smidighet fremmer en kultur for kontinuerlig læring, tilpasning, og kundesentrert utvikling, som er essensielt for å opprettholde relevans og suksess i medieindustrien. Samtidig identifiserer oppgaven utfordringer knyttet til implementeringen av smidige metoder, inkludert behovet for balanse mellom fleksibilitet og struktur, samt viktigheten av effektiv kommunikasjon og samarbeid på tvers av forskjellige avdelinger. I diskusjonsdelen vurderes funnene i lys av eksisterende litteratur, og oppgaven reflekterer over hvordan smidige metoder kan videreutvikles og tilpasses for å møte mediebransjens unike behov. Avslutningen viser til de viktigste funnene rundt korte sprint perioder, pause perioder mellom sprintene og hvordan bedriftene i studien har delt opp ansvarsområder for de forskjellige avdelingene. Det kommer også frem hvordan det å produsere resultater har et mye høyere fokus enn å vise til prosessen rundt.

Oppgaven bidrar med verdifull innsikt i det praktiske arbeidet med smidig utvikling i mediebransjen, og tilbyr veiledning for bedrifter som ønsker å forbedre sine smidige praksiser. Den avslutter med forslag til videre forskning som bygger på de etablerte funnene.
Abstract
Denne oppgaven undersøker skyttergravsdynamikk og ekkokammer i norsk nettdebatt i lys av Antonsen-saken. Oppgaven tar utgangspunkt i hvordan rasisme, hets og kjønnsdiskriminering kommer til utløp i kommentarfeltene på digitale plattformer, spesifikt Facebook og ulike nettaviser. Antonsen-saken, der komiker Atle Antonsen ble anmeldt for hatefulle ytringer mot samfunnsdebattant Sumaya Jirde Ali for å ha sagt blant annet «du er for mørkhudet til å være her» danner grunnlaget for å forstå diskursen i norsk digital offentlighet.

Oppgaven tar utgangspunkt i hvordan den digitale offentligheten har gjort det mulig for virtuelt hvem som helst å ytre seg, noe som kan ha ført til en økning i hets og diskriminerende holdninger på nett. Med skyttergravsdynamikk og ekkokammer i sentrum, undersøker jeg hvordan disse fenomenene bidrar til å opprettholde og forsterke hatefulle ytringer. Målet med oppgaven er å vise hvordan Antonsen-saken kan bidra til å forklare disse dynamikkene i norsk nettdebatt.

Sentrale begreper som digital offentlighet og fragmentering skal forklare og støtte funnene i oppgaven. Jeg diskuterer hvordan den digitale offentligheten gir rom for ytringer som kan oppfattes som politisk ukorrekt og støtende i den fysiske verden, men som gjerne uttrykkes når det fysiske aspektet uteblir.

Alternative og sosiale medier skaper nye utfordringer ved at debattanter angriper hverandre uten å søke felles forståelse. Den digitale offentligheten er ikke bundet til én nettside, men til hundrevis av mediekanaler farget av forskjellige ideologier, argumenter, meninger og verdensoppfatninger. Nettdebatten blir dermed uoversiktlig og kompleks. For å bekjempe desinformasjon, diskriminering og desorientering er det nødvendig å gjenkjenne ekkokamre og skyttergravsdynamikk i ulike typer medier. Gjennom denne oppgaven utforsker jeg hvordan disse debattarenaene fungerer i praksis, og hvordan det ofte oppstår en ikke-debatt i debatten.

Alsvåg S.,  Addressing the Next-Poster Problem: A Hybrid Recommender System for Streaming Platforms, together with TV 2, UiB, Bergen 2024. Supervisor: Christoph Trattner

Abstract
Recommendation strategies in the Movie domain is varied, but has been shown to aid users in finding content they like. On video streaming-platforms such as TV 2 Play, the user is exposed to several different arenas where they can find something they would like to watch, be that the landing-page of the streaming site, or a suggestion for something more to watch after they concluded a movie or series. These are all areas where Recommender strategies can recommend something based on either the preferences of the user, or in the case of the concluded movie or series, something more to watch based on what they just watched. This latter aspects, being what I refer to as the next-poster problem in this thesis, is not a largely explored area of research, where previous actors have simply utilized the already established Collaborative Filtering (CF) model concerned with the user’s preferences without considering what the user just watched. Here I show that a solution to the next-poster problem is to combine the CF model with a Sequence Aware approach based on Markov Chains, finding an increase in implied user satisfaction over the baseline CF approach. Through an online evaluation on the streaming platform TV 2 Play, I show that using a Hybrid approach to solve the next-poster problem rather than a traditional CF model leads to a lessening in user engagement such as CTR, but an increase in the clicks resulting in a user actually watching the content, this being our implied user satisfaction. Further as a result of this online evaluation, I am able to show that its possible to find the best configuration for a Hybrid model based on Sequence Aware and CF approaches deployed in a real life scenario, through offline evaluation. The results allows me to showcase the importance of considering Sequence of items when recommending for the next-poster problem, and to show that an offline evaluation can imply results in a real world scenario, when considering the Movie domain. Although an improvement, this thesis also shows that there are many more avenues to consider for the next-poster problem.

Rosenvinge F., Automated Identification of Severe Errors in Speech to Text Transcripts, together with TV 2, UiB, Bergen 2023. Supervisor: Samia Touileb, Lubos Steskal.

Abstract
In this thesis we explore how problematic misplaced words can be automatically identified in speech-to-text-transcripts. Automatic Speech Recognition systems (ASR) are systems that can automatically generate text from human speech. Because natural language spoken by humans is complex, due to dialects, variations in talking speed, and differences in how humans talk compared to the training data, there might be errors introduced by such ASR systems. Sometimes, these errors are so bad that they become problematic. Post-processing of an ASR system means finding such errors after the text has been generated by the system. We want to find out to what degree probabilities of words computed using pre-trained language models can be used to solve this problem, as well as to what degree these probabilities can be used to create a classifier to detect problematic words. We present our solution, where we synthetically introduce problematic words into text documents. Then we compute probabilities of both problematic and non-problematic words in these documents to investigate if they are treated differently by the models. We show that the models generally assign lower probabilities to problematic words and higher probabilities to good words. We train a logistic regression classifier using these probabilities to classify words. Our results show that using probabilities from NorBERT1 and NorBERT2, a logistic regression classifier can accurately detect problematic words. We also show that NB-BERT performs worse than a baseline bigram model.

Sviland V., Designing Map-Based Visual Storytelling for News Articles in Mixed Reality, UiB, Bergen 2023. Supervisors: Frode Guribye.

Abstract
his study investigates how we can design map-based visual storytelling of news articles for Mixed Reality Head-Mounted Displays (MR HMDs). It explores the significance of visual storytelling genres and interactive gestures in the design. The findings reveal that principles of storytelling and interaction cannot be directly transferred from traditional PC interfaces to MR HMDs due to fundamental differences in interface and interaction. The study highlights the effectiveness of the dynamic slideshow format and far-interaction in enhancing the storytelling experience. Participants favored hand interactions but expressed interest in alternative methods such as gaze- and voice-based interactions. The challenges faced during the project, including recruitment difficulties, testing environment limitations, and technical issues, influenced the findings. The study emphasizes the need for tailored design principles for MR storytelling and multiple interaction methods to cater to user preferences. Overall, the findings provide valuable insights into designing map-based interactions in MR for visual storytelling, with consideration for the encountered challenges and limitations.

Røysland Aarnes P., Named Entity Recognition in Speech-to-Text Transcripts, together with TV2, UiB, Bergen 2023. Supervisors: Samia Touileb, Lubos Steskal.

Abstract
Traditionally, named entity recognition (NER) research use properly capitalized data for training and testing give little insight to how these models may perform in scenarios where proper capitalization is not in place. In this thesis, I explore the capabilities of five fine-tuning BERT based models for NER in all lowercase text. Furthermore, I aim to measure the performance for classifying named entity types correctly, as well as just simply detecting that a named entity is present, so that capitalization errors may be corrected. The performance is assessed using all lowercase data from the NorNE dataset, and the Norwegian Parliamentary Speech Corpus. Findings suggest that the fine-tuned BERT models are highly capable of detecting non-capitalized named entities, but do not perform as well as traditional NER models that are trained and tested on properly capitalized text.

Espeseth F., Media Analytics for Personalization and Advertisement, together with Amedia, UiB, Bergen 2023. Supervisors: Mehdi Elahi, Igor Pipkin.

Abstract
In the realm of advertising, strategic placement and presentation of advertisements are crucial for attracting potential clients. Media companies employ various tactics, such as visually appealing features and vibrant colors, to capture the attention of consumers. However, achieving this objective is not always straightforward, as some advertising strategies may be perceived as irrelevant or disturbing by recipients. This Master’s thesis aims to explore the relationship between audience interaction and the perception of advertisements on media platforms, with the overarching goal of enhancing advertising effectiveness and addressing ethical concerns associated with targeted advertising. To delve into this topic comprehensively, this study utilizes real-time data provided by Amedia, one of the largest media companies in Norway. Through an extensive analysis of this real-world data, the research aims to explore the correlation between audience interaction and the perception of advertisements on media platforms. This investigation involves the extraction of relevant features from advertisement images, leading to the creation of a new dataset. Concurrently, predictive machine learning models are developed to gain insights into effective advertising strategies for media companies, with a focus on personalization. Furthermore, a comprehensive user study is conducted to gain insights into user behavior within media platform advertisements. By uncovering the interplay between visual features, user behavior, and advertising effectiveness, this research contributes to improving personalized advertising strategies in the context of media companies.

Bergh S.,  Personalized Recommendations of Upcoming Sport Events, together with TV 2, UiB, Bergen 2023. Supervisor: Mehdi Elahi.

Abstract
Recommender systems have emerged as essential tools for enhancing user engagement and content discovery in various domains, including the sports industry. In the context of sports viewing, personalized recommendations have become increasingly significant, enabling users to easily connect with their favorite sports teams, explore new content, and broaden their viewing preferences. Collaborative filtering (CF) stands out as a popular recommendation algorithm that analyzes the similarities and patterns in user-item interactions. By examining the behavior and preferences of a group of users, CF identifies similar users and recommends items that have been positively received by those with similar tastes. Applying CF to sports recommendations presents an opportunity to introduce users to new sports events enjoyed by their peers. However, recommending upcoming live sports events introduces unique challenges, such as limited availability and the need to strike a balance between catering to users’ favorite sports and introducing them to new content. This master thesis aims to address these challenges through the development of a personalized recommendation system for upcoming sports events using CF. The system will analyze user viewing history to provide tailored recommendations that facilitate content discovery and enable users to easily locate their preferred sports events. The research objectives include identifying the most suitable collaborative filtering model for sports content recommendation, investigating the factors that influence sports fans’ preferences for specific types of live sports events, and evaluating the effectiveness of personalized recommendations compared to non-personalized approaches. The proposed system is implemented and A/B tested on TV 2 Play, one of Norway’s largest digital streaming platforms, with the ultimate goal of enhancing user experience and engagement by delivering personalized and relevant recommendations for sports content. This research contributes to the field by proposing a novel collaborative filtering recommender for sports based on user viewing sessions, exploring effective strategies for recommending upcoming live sports events, and assessing the system’s performance in terms of accuracy and user satisfaction.

Forstner S., Designing a Dyslexia-Friendly Interaction with News Articles, UiB, Bergen 2023. Supervisor: Bjørnar Tessem.

Abstract
This master’s thesis presents a research project focused on improving the accessibility of news articles for people with dyslexia. A significant portion of online news content is text-based, which poses challenges for individuals with reading difficulties. While there are existing digital tools for text simplification and summarization, there is a lack of solutions specifically designed for dyslexic readers, and even fewer adapt to languages other than English. The project addresses this gap with the development of a prototype that generates simplified versions of Norwegian news articles. Adopting a user-centered perspective, qualitative research methods and literature research were conducted to provide a basis for the design process. The later developed prototype aims to provide a flexible model that can accommodate the different reading experiences and perspectives of dyslexic people. Its main functionality lies in visual and content-related text modifications. Together with results from corresponding user tests, the high-fidelity prototype provides detailed findings on how news articles can be made more accessible. They offer insights into the requirements and needs of news consumers with dyslexia and explore the potential of automatic text simplification in this context. The results can benefit companies, institutions, and organizations that are seeking to provide accessible news content, eliminating the need for manual simplification of every article. Moreover, the research conducted in this project can support further studies on design and digital accessibility solutions.

Hansen K., Nyheter fortalt slik unge voksne liker det, UiB, Bergen 2023. Supervisor: Brita Ytre-Arne. 

Abstract
Nyhetspodkastene Aftenposten Forklart og NRK Oppdatert ligger uke etter uke på topplisten over de mest lyttede podkastene i Norge. Til tross for nyhetsformatets økende popularitet, har det til nå vært lite forskning på hva det er med formatet som appellerer til unge voksne. Dette masterprosjektet undersøker nyhetspodkaster, og hva det er med formatet som appellerer til unge voksne. Ved å intervjue 11 informanter som lytter til nyhetspodkaster ukentlig, vil denne masteroppgaven undersøke hvilke faktorer som er relevante for unge voksne sin opplevelse av nyhetspodkaster, og hvordan det er å få nyheter i podkastformat sammenlignet med andre nyhetsmedier. Funnene i denne undersøkelsen viser at nyhetspodkaster er en engasjerende måte å få med seg nyheter, og bruken av fortellingsteknikker i formidlingen er en hovedgrunn til at informantene velger å lytte. Sammenlignet med tradisjonelle nyhetsmedier viser funnene fra studien at nyhetspodkaster hjelper lytterne med å få en bedre oversikt og forståelse av dagsaktuelle nyheter.

Jahr O., Creating an Agglomerative Clustering Approach Using GDELT, UiB, Bergen 2023. Supervisor: Andreas L. Opdahl.

Abstract
GDELT is a project with a large scale, continuously updated databank that provides a real-time image of the global news picture by outputting these as files that can be downloaded and used by anyone. However, this data is of low granularity, and each source of data does not provide much information on its own. This thesis attempts to leverage the large amount of data available by utilizing a Hierarchical Agglomerative Cluster method to identify news articles that report about the same real life event. To do this, the thesis also explores if the GDELT data is granular enough to be used without extensive preprocessing, and if a distance metric for the cluster algorithm can be created. The findings show promising results when regarded with qualitative measures, but the quantitative measures are not yet optimized. Inherent flaws in GDELT and clustering algorithms are a hurdle to be overcome before the real potential of GDELT’s data can be unleashed, and this thesis will explore some of these difficulties and make recommendations for how to circumvent them in future works.

Kirkhorn T., Generative språkmodeller for automatisert tekstforenkling: Tilpasning av nyhetsartikler for lesbarhet hos personer med dysleksi, together with NRK and NTB, UiB, Bergen 2023. Supervisor: Bjørnar Tessem.

Abstract
I denne masteroppgaven utforskes utviklingen av en prototype for automatisert tekstforenkling med fokus på tilpasning av nyhetsartikler for personer med dysleksi. Prosjektet involverer flere iterasjoner for å finne den mest effektive tilnærmingen for å forenkle tekstene ved hjelp av generative språkmodeller. Prototypen inneholder tre nivåer av forenklet tekst, der nivå null representerer den originale teksten og nivå en til tre gradvis forenkler innholdet. Testing og evaluering av prototypen gjennomføres ved å utføre brukertester med målgruppen og samle tilbakemeldinger fra eksperter innen feltet. Disse tilbakemeldingene er verdifulle i forbedringen av prototypen og tekstforenklingen. En viktig del av arbeidet er eksperimentering med ulike prompts og instruksjoner for å finne den mest effektive måten å be språkmodellen forenkle artiklene på. Observeringer indikerer at formuleringen av promptene har en innvirkning på resultatene, og at det er utfordringer knyttet til språket i de genererte versjonene. Dette vil kreve manuell redigering av tekstene for å oppnå ønsket lesbarhet og kvalitet. Funnene indikerer at språkmodellen fortsatt har begrensninger når det gjelder å generere grammatisk korrekte setninger og å velge passende ord i konteksten ved omformulering av en eksisterende tekst. Videre identifiseres utfordringer knyttet til maksgrensen for tokens, som begrenser promptlengden, artikkellengden og den forenklede teksten. Det er viktig å påpeke at denne forskningen blir gjennomført innenfor de nåværende rammene for språkmodeller for å teste reformulering av norske nyhetsartikler. Med fremtidig utvikling av språkmodeller og økende tokenkapasitet, samt inkorporering av retningslinjer for klarspråk direkte i modellene, kan vi forvente ytterligere forbedringer i automatisert tekstforenkling.

Klingenberg P., Using content- and behavioural data for recommendations in the Norwegian news market, together with BT, UiB, Bergen 2023. Supervisor: Mehdi Elahi.

Abstract
In the news domain, the technological development has contributed to always accessible platforms with frequent publishment of articles. This leads to a vast amount of articles, in addition to a multitude of choices. Interactions executed by users (clicks, views or ratings) and content of articles (text, section, etc.) on such platforms can be utilized to create personalised recommendations. However, there can arise a situation where there is a lack of data, i.e., when a new article is published or there is a new user, known as the cold start problem. In addition, personalised recommendations in the news industry, where user behaviour are the basis of recommendations, are more complex in comparison with, for example, the movie domain due to the timeliness with short duration and relevance of articles. Recommendations provided by content data may mitigate this issue. This thesis investigates the viability of using both content- and user-behavioural data to generate recommendations in the Norwegian media market in collaboration with one of Norway’s largest newspapers, i.e., Bergens Tidende (BT). The first technique investigated is collaborative-based filtering, built on the recommender models Alternating Least Squares, Bayesian Personalized Ranking and Logistic Matrix Factorization, which is specially tailored to use user behavioural data as input. The second technique investigated is content-based filtering, built on a state-of-the-art architecture named BERT, specially trained to draw the semantic content of sentences in the Norwegian language. A comprehensive offline evaluation of both techniques is executed using dimension reduction and a diverse selection of accuracy metrics. In addition, an online evaluation of a large-scale A/B test of the content-based filtering technique against a former recommendation technique in BT is performed. The evaluation methods used in the online experiment are descriptive data- and Bayesian analysis. The results of the collaborative filtering technique have shown increased performance in different stages of filtering, in addition to the importance of hyperparameter tuning. The results have shown promising performance based on the content-based filtering technique, indicating that this attracts users’ interest at a greater scale, even the groups that usually show less interaction.

Moholdt E., Detecting Out-of-Context Image-Caption Pairs in News: A Counter-Intuitive Method, UiB, Bergen 2023. Supervisor: Duc-Tien Dang-Nguyen.

Abstract
The growth of misinformation and re-contextualized media in social media and news along leads to an increasing need for fact-checking methods. Concurrently, the recent advancement in generative models enables a new method of spreading misinformation via AI manipulated images and videos. With the advent of deep-learning technologies used to create ‘deepfakes’ and generative models that can produce near realistic images from text prompts, fabricated media is getting increasingly hard to detect. The media covered in this project is re-contextualised media referred to as ‘cheapfakes’, which consists of image and its associated captions. For example, an image might appear in different online sources with different caption claims. The field of generative models is currently experiencing rapid growth. While text-to-image generative models can potentially be misused for ‘deepfake’ creation and spreading misinformation, this thesis present a positive application. In this thesis we present a novel approach using generative image models to our advantage for cheapfake detection. We present two new datasets with a total of 6800 images generated using two different generative models including (1) DALL-E 2, and (2) Stable-Diffusion. We propose text-to-image generative models can be employed to detect out-of-context media. The similarity or dissimilarity of the generated images versus the original image may serve as an indicator of opposing or misleading captions containing out-of-context news. We evaluate and employ a handful of methods for computing image similarity. Our cheapfake detection model is the first of its kind that utilizes generative models, and we achieve a 68% accuracy score for cheapfake detection, proving that image generation models can be utilized to efficiently detect cheapfake media. Our models similarity measures also align with human perception of image similarity. Moreover, we outline several opportunities for optimization. We are confident that the method proposed in this thesis can further research on generative models in the field of cheapfake detection. We are confident that the resulting datasets can be used to train and evaluate new models aimed at detecting cheapfake media and would further research in this area.

Johannessen Skivenesvåg , M., Evaluating Pre-trained Language Model Strategies for Knowledge Graph Extraction: A Comparative Analysis, UiB, Bergen 2023. Supervisor: Andreas Lothe Opdahl.

Abstract

Nilsen A., Investigating the Effects of Instagram Filters on Perceived Trust in Online News Posts, UiB, Bergen 2023. Supervisor: Alain Starke, Christoph Trattner.

Abstract
The increasing overgrowth of information is only getting harder to navigate through and the spread of fake news and misinformation is concerning. With the shift towards digital deliv- ery of news and concerns about the accuracy and reliability of information shared on social media, it is important to understand the factors that contribute to trust in social media news. Motivated by these challenges, this study aimed to investigate what effect Instagram filters have on users’ perceived trust in online news posts. Trust ratings of four different articles with four different image filters, including the original image, were collected through an on- line user study. Also, the role of general trust and familiarity with the topic and the context of the different topics were explored. We did an online experiment with 204 participants recruited from a crowdsourcing platform. Participants were asked to answer six questions per online news post shown. Our analysis revealed that while Instagram filters overall may not affect perceived trust, specific visual characteristics of the filters such as brightness and contrast may play a role. Additionally, individual differences in general trust and attitude to- wards the topic may influence the users’ perception of trust. The study also found that there may be differences in perceived trust across different news topics. Thus, there could be other factors influencing the users’ participants of trust.

Gjelsvik Lunde M., Fine-Grained News Classification, UiB, Bergen 2023. Supervisor: Enrico Motta.

Abstract
This thesis investigates the concepts of fine-grained news classification. To do this, an empirical study in which human annotators categorized news was conducted. The also study consisted of measuring agreement between hu- man annotators and evaluating the precision of the annotations. The study revealed a need for a framework for fine-grained news classification. A framework was then developed and evaluated, producing a complete annotated dataset.

Rosnes D., Evaluating Feature-Specific Similarity Metrics using Human Judgments for Norwegian News, UiB, Bergen 2023. Supervisor: Christoph Trattner, Alain Starke.

Abstract

This master’s thesis delves into the measurement of similarity between news articles within the Norwegian news domain. Four central questions form the basis of the thesis: the identification of information cues utilized by readers, the effectiveness of specific similarity metrics, the comparison with other domains, and the exploration of differences in human similarity ratings between national and local news. Key findings include that a Sentence-BERT metric, applied to the body text, best represented human similarity judgments. Compared to other news domains, the Norwegian news domain showed stronger correlations for a majority of the metrics. A minimal contrast was observed between human ratings for local and national news, with local news considered slightly more similar. This disparity between local and national levels, however, did not markedly impact how metrics represented human similarity judgments. The findings from this thesis may provide valuable insights for enhancing news recommendation systems within the news sector.

Ulvolden H., Complexity-based Ordering of Suffixes in Norwegian, UiB, Bergen 2023. Supervisor: Koenraad de Smedt. 

Abstract
Denne studien undersøker bruken av 18 avledningssuffikser i norsk bokmål, og har som mål å replikere studien gjort av Hay and Plag (2004). Studien deres forsøkte å forklare hvordan restriksjoner på affikskombinasjoner bestemmes av såkalt kompleksitetsbasert sortering. Den viser at et suffiks har større sannsynlighet for å plasseres etter et annet suffiks hvis det er mer produktivt (i stand til å produsere nye ord) og mer parserbart (lettere for en språkbruker å separere fra baseordet sitt). På samme måte har jeg brukt korpusmateriale til å finne ut hvilke kombinasjoner av to suffikser som finnes i norsk. Deretter har jeg brukt korpus til å samle informasjon om suffiksenes produktivitet og parserbarhet. Produktivitet måles ved å sammenligne proporsjonen av hapaxer (ord som kun dukker opp én gang i et korpus) med det totale antallet ting som inneholder nevnt suffiks. Parserbarhet måles ved å sammenligne frekvensen av avledninger med frekvensen av baseord (f.eks. ærlighet og ærlig), som viser hvor sannsynlig det er at en språkbruker oppfatter dem som enkelte ord istedenfor et baseord med et suffiks. Suffikskombinasjoner ble organisert i et hierarki basert på hvilke suffikser som kan opptre etter andre. Resultatene viser at i motsetning til i engelsk kan noen kombinasjoner også opptre i motsatt rekkefølge, og affikser kan derfor ikke organiseres i et like strengt hierarki som i engelsk. Resultatene viser også en korrelasjon mellom produktivitet og parserbarhet, dvs. at et produktivt suffiks også har lettere for å separeres fra baseordet sitt. Vi ser også en viss sammenheng mellom disse to faktorene og suffikshierarkiet. Selv om det er vanskelig å si hvor mye dette henger sammen, er det tydelig at mange av de fleksible suffiksene som kan plasseres etter andre også er mer produktive og parserbare.

Vlasenko A., Multi-List Recommendations for Personalizing Streaming Content, together with TV 2, UiB, Bergen 2023. Supervisor: Christoph Trattner. 

Abstract
The decision behind choosing a recommender system that yields accurate recommendations yet allows users to explore more content has been a topic of research in the last decades. This work attempts to find a recommender system for TV 2 Play, a movie streaming platform, that would perform well on implicit feedback data and provide multi-lists as recommenda- tions. Several approaches are examined for suitability, and Collaborative Filtering and Multi- Armed Bandits are decided upon. The models for each approach are built using the pipeline utilized by TV 2 Play. The models are then compared in performance on several evaluation metrics in the first stage of offline testing, yielding Alternating Least Squares and Bayesian Personalized Ranking as the best-performing models. The second stage of offline testing includes testing the two models and their variants with the BM25 weighting scheme applied against each other. The unweighted Bayesian Personalized Ranking model has shown the highest user-centric metrics while maintaining relatively high recommendation-centric met- rics, which led to that model being tested in online settings against the algorithm currently used by TV 2 Play team. The online testing has revealed that our model underperforms compared to the TV 2 Play model when used on the kids’ page but produces equally good results on the movies page. The results can be attributed to the differences in behavioral content consumption patterns between users.

Westli W., Minimum ressursbruk. Maksimum utbytte., together with TV 2, UiB, Bergen 2023. Supervisor: Lars Nyre.

Abstract
The media industry is constantly changing and it is therefore important for companies to keep up with technology. Until 2021, TV 2 had had the same logo for almost 30 years, and as TV 2 CEO Olav Sandnes said during a general meeting in 2021, “…TV 2 in recent years (…) has taken big steps in the digital and within streaming without the brand having kept up.” (Hauger, 2021). At the same time as the public’s external profile has changed, the internal following must also keep up. This master’s thesis is a discussion of how student projects should be set up in order to get as good a starting point and result as possible when collaborating with a media company. The focus is on planning student prototypes to turn them into products. I use theories taken from Lim et.al. his article “The Anatomy of Prototypes” about how prototypes are built and the process around them, while I use the approaches and methods from Eric Ries’ “The Lean Startup” and Jake Knapp’s “Sprint”. The analysis work is set up so that I analyze the tools we have created for the prototype “TV 2 Pippen Relevans”, before I then go into what is needed to create a prototype that can become a product.
Abstract

Postponed access: the abstract will be accessible after 2024-06-01.

Ekren K., Experiments on Satire Detection for Norwegian News Articles, together with Web64, UiB, Bergen 2022. Supervisor: Samia Touileb.

Abstract

The spread and amount of misinformation is increasing. The World Economic Forum (WEF) has listed it as one of the main threats to our society (Howell, 2013). Satire is one of the problems when it comes to misinformation, more specifically news satire. News satire is a genre of satire that resembles the characteristics of true journalistic reporting, while keeping the main objective of satire that is: use of a combination of humor and irony, usually with exaggeration, to expose and make fun of political or newsworthy issues.

In this thesis we present to the best of our knowledge, the first attempt to automat- ically detecting satire in Norwegian news articles. Automatically identifying satirical news pieces can aid in minimizing the potential deceptive impact of satire. To this end, we employ three classification methods, namely Naïve Bayes, SVM (support-vector machines) and logistic regression, based on TF-IDF (Term Frequency Inverse Docu- ment Frequency) feature weights. All three machine learning models achieved similar results.

In total, our dataset incorporates 6322 articles containing a balanced collection of satirical and non-satirical news texts from various domains (3161 satirical and 3161 non-satirical). Using this corpus we proposed three cross-domain satire detection tasks, one considering only the use of headlines, one considering only the use of article texts, and lastly one considering full articles, including both headlines and texts.

After experimenting on the test sets, we achieved the top accuracy score of 98% using only text as input, and the combination of title and text as input, with SVM. We observe that satire detection on news headlines was significantly more challenging, the top accuracy score being 76% using SVM. We believe that this shows that the automatic detection of satire using only headlines is quite challenging. Especially when using simple machine learning approaches, and we believe that this might be due to the length of headlines and the need for more context.

Abstract

Irony is a complex phenomenon of human communication and due to its con- textual nature has been notoriously difficult for machine learning algorithms to detect. With an established practical definition of irony based in the environ- ment of Facebook comment sections. Used together with a Norwegian language pre-trained BERT model converted to a long version that supports longer text inputs, and a Norwegian Facebook comment dataset with contextual article and reply comment text included. It was found that the long BERT model trained on the context included inputs dataset outperformed the short BERT models trained on datasets of the same and more comments, but without the contextual infor- mation encoded.

Jakobsen D., Visual analysis, recommendation and personalization, UiB, Bergen 2022. Supervisor: Mehdi Elahi.

Abstract

Advertisement is one of the primary sources of revenue for companies. Advertisement can result in increased sales for the companies by promoting their products or by hosting the advertisement of the other companies. While there have been many studies investigating the effectiveness of the advertisement in various domains, there are still challenges to be addressed. Notable challenges are overabundance, privacy, spamming, or irrelevant placement of advertisement. The results of such challenges can be poor quality of advertisement irrelevant to the audience interest or irrelevant in the context of the content in which it has been shown. A colourful and shiny image in an advertisement, promoting a luxury product that is placed together with a news article discussing the growing poverty in certain regions of the world can be an example. This can lead to dissatisfaction of the audience when experiencing a particular irrelevant advertisement. Personalisation techniques can be useful in addressing such challenges. For example it can be used to match the advertisement shown in news outlets to the article. Such techniques can analyse the content of the news articles and find right advertisement that is better suited to the article. However, this requires rich data of displayed advertisement which are not always available. That can be one of the reasons why viewing an irrelevant advertisement is still part of our everyday experience. In this thesis, I have explored the potential of using automatic visual analysis to obtain better representation of the advertisement and to improve the relevance of advertisement to the audience. For such analysis, a number of visual features has been extracted from the images of the advertisements and analysed to better understand their correlations with audience behaviour online when interacting with advertisement campaigns. I have received the data set from Amedia, one of the largest media companies in Norway. The data set includes campaigns and audience behaviour, and the images associated with the campaigns. Four analyses have been conducted in the thesis including, exploratory analysis and correlation analysis. Machine learning models have been built (using CatBoost) based on the audience behaviours and visual features extracted from advertisement. In addition a method called SHAP (SHapley Additive exPlanations) has been used to find explanation of model prediction. The contribution of this thesis includes preprocessing and exploratory analyses of the industry data, a novel data set containing the visual features extracted from the images of the advertisement, a Python prototype, and the results of analyses based on this prototype.

Johansen S., Expanding Digital Workspaces Using Cross-Device Interactive Applications, UiB, Bergen 2022. Supervisor: Morten Fjeld.

Abstract

In this thesis I explore the use of a cross-device interactive application and how single individuals could make use of multiple connected devices by themselves for their work. I have created a functional prototype that is used to evaluate the workload of a single device versus the use of multiple devices with the use of in-built cross-device interaction capability. The process of this study consisted of research, prototyping, programming the application, and performing a study to analyze the data gathered. Due to the covid-19 situation, the project had major re-routes in 2021 to handle its effects, resulting in an additional year of work to complete it.

Khutarniuk Y., Cross-Lingual Approaches to Identifying Argument Components and Relations in Norwegian Reviews, UiO, Oslo 2022. Supervisors: Samia Touileb, Lilja Øvrelid.

Abstract

Argument mining is the process of automatic extraction of certain argu- mentation structures from data. Argument mining consists of several stages such as argument component detection, argument component clas- sification, and argumentative discourse analysis. The lack of training data in low resource languages is a common issue in argument mining applica- tions. In this work we analyse the possibilities for the application of zero- shot and few-shot language transfer models trained on the language ma- terial in a resource-rich language (English) for the tasks of argument com- ponent detection, and argument component classification in a low-resource language (Norwegian) with the aim to find out if these techniques can help overcome the challenge of no available training data. In addition, we com- pare models based on different transformer architectures and experiment with additional hand-crafted features.

Olsen D., Movie Recommendation based on Stylistic Visual Features, together with TV 2, UiB, Bergen 2022. Supervisor: Mehdi Elahi.

Abstract

When a new movie is added to the catalogue of a recommendation-empowered movie streaming platform, the system exploits various types of data (e.g., clicks, views, and ratings) in order to generate personalized recommendations for the users. However, in the absence of sufficient data, undesired situations can arise where the system may fail to include the new movie in the recommendation list. This is known as the Cold Start problem. A solution can be using content features attributed to the movies (e.g., tags, genre, and description). However, such features require expensive editorial efforts and it is not necessarily available in good quantity or quality.

This thesis investigates the viability of using novel stylistic visual features as meta- data to incorporate in the movie recommendation process. The visual features represent the stylistic properties of the movies and can have a wide range of forms, e.g., color palette, contrast, and brightness. The stylistic visual features can be automatically ex- tracted, and hence, do not require any (manual) human annotation. Accordingly, the thesis proposes a novel technique for generating recommendation based on such visual features and describes the technical details for different stages of the process. The tech- nique has been evaluated in both offline and online experiments and different scenarios, i.e., cold start and warm start. The online experiment has been conducted in collabo- ration with TV 2, one of Noways largest digital streaming platforms adopting an A/B testing methodology. The proposed technique includes utilizing the extracted visual features when used individually (in a similarity based recommendation process), and when combined with other types of data (in a hybrid recommendation process). The results of the experiments have been promising and shown that the stylistic visual fea- tures can be beneficial particularly in the hybrid recommendation process in the cold start scenario.

Solberg V., News Recommendation based on Human Similarity Judgment, together with Bergens Tidende, UiB, Bergen 2022. Supervisors: Christoph Trattner, Alain Starke.

Abstract

Similar item recommendation is one of the most popular types of recommender systems. As the name implies, the objective is to recommend items that are similar to a reference item. The news domain is one of the many that employ this form of recommendation, which utilize similarity functions in order to calculate the similarity. In this study, human judgments of article similarity were acquired using an online user study in which each of the 173 participants evaluated the similarity of 12 pairs of articles. Each of the 12 article pairs had their own unique characteristics. One pair would be made up of two completely dissimilar articles, while the other pairs had either a shared topic, a named entity in common, publication dates in close proximity, or some combination of these three characteristics. Half the pairs contained articles from the News (i.e., recent events) category, while the other half contained Sport articles. The similarity of the same article pairings was then calculated utilizing various similarity functions, and the correlation between human judgment and function scores was computed. This thesis found that the correlation ranged from weak to strong, depending on the function. The thesis also found that the correlation is largely dependent on the whether the articles have certain characteristics in common. On average, the functions correlated more strongly to human judgment if the articles belonged the category News (i.e., recent events) than Sport. The functions were also better at predicting human similarity when the articles in question were relatively similar to one another. The novel work presented in this thesis shows that the correlation between human judgment and similarity functions can be stronger than previous work has suggested, if news articles are paired in a meaningful way.

Stenerud B., Reaksjonsvideoer. En studie av unge voksnes opplevelser med mediefenomenet reaksjonsvideoer, UiB, Bergen 2022. Supervisor: John Magnus Dahl.

Abstract

Denne oppgaven undersøker hvordan unge voksne benytter seg av mediefenomenet reaksjonsvideoer. Ettersom plattformer som YouTube og Twitch blir mer populære og sentrale i folks hverdag vil man naturligvis også bli smittet av trender. Den siste tiden har det blitt populært med reaksjonsvideoer som handler om at streamere eller innholdsprodusenter filmer seg selv reagere til hva enn som skjer på skjermen deres. Et eksempel på dette er Asmongold som har rundt 200 000 seere på hans livestream av at han selv reagerer og kommenterer på rettsaken til Johnny Depp og Amber Heard. Fenomenet vil bli sett i lys av opinionsledere og parasosiale relasjoner. Gjennom kvalitative dybdeintervjuer tar studiet for seg 10 informanters opplevelser, samt hva de får ut av fenomenet. Studien ser og på hvordan informantene selv tolker og forklarer fenomenet, og hvordan de bruker reaksjonsvideoer annerledes fra «vanlige» videoer. Funnene i denne studien tyder på at informantene bruker reaksjonsvideoer som en måte å få mer informasjon om det man ser på, og for å få inn flere perspektiver. Reaksjonsvideoer bidrar og til økt selskap mens informantene ser på videoene. På denne måten opplever informantene at de ser på en video «med» noen som de kan føle at de kjenner. Man kan også se at informantene bruker reaksjonsvideoer, og kommentarfelt, som en måte å bekrefte egne tanker og meninger, samt at slike videoer fungerer som en måte å se på andre gjenoppleve det man selv har gjort.

Kvasnes Olsen D., Movie Recommendation based on Stylistic Visual Features, UiB, Bergen 2022. Supervisor: Lars Skjærven, TV 2.

Abstract

Årmot I., Smarttelefonen som ein del av konsertopplevinga, UiB, Bergen 2022. Supervisor: John Magnus Dahl.

Abstract

Smarttelefonen er ein integrert del av kvardagslivet vårt og me brukar den til fleire praktiske formål, og upraktiske. I kvardagen blir smarttelefonen hylla fordi den har fleire bruksområder, men samtidig kan den bli slakta for evne si til å forstyrre merksemda vår, eller forstyrre andre som irriterer seg over andre sin bruk i situasjonar dei skulle helst vore forutan. Denne masteroppgåva prøvar å kome med eit bidrag til studiar om smarttelefonbruk i eit medieerfaringsperspektiv. Med inspirasjon frå irritasjonen enkelte publikummarar uttrykkjer i kronikkar og lesarinnlegg om andre publikummarar sin bruk av smarttelefonen gjennom ein heil konsert, undersøkar denne oppgåva korleis unge vaksne frå alderen 20 til 26 år brukar smarttelefonen i ein konsertsamanheng. Ved å utføre deltakande observasjon av konsertane til Daniel Kvammen og Kjartan Lauritzen på USF Verftet i Bergen, etterfølgt av kvalitative intervju i etterkant av utvalde publikummarar, prøvar denne oppgåva å svare på korleis smarttelefonen er ein del av ei medieerfaring av å reise på konsert. I eit medieerfaringsperspektiv undersøker oppgåva korleis informantar brukar smarttelefonen på konsertane til Daniel Kvammen og Kjartan Lauritzen. Altså kva tar dei bilete og videoar av? Kvifor deler dei bileta og videoane med andre? Kva slags betydingar har det for informantane å dele konsertbileta og -videoane? Funna i analysen kan indikere at informantane ikkje er opptekne av å bruke smarttelefonen heile tida på konsertane til Daniel Kvammen og Kjartan Lauritzen ettersom det kan forstyrre ein tilstand av flow. Likevel brukte informantane smarttelefonen for å ta bilete og videoar av konsertane, og med tanke på at smarttelefonen kan verke å vere naturalisert i liva til informantane i den grad at dei ikkje tenkjer over bruken lengre, kan det tyde på at smarttelefonen er ein del av flowen. Naturaliseringa av smarttelefonen i liva til informantane kan også gjere det naturleg for dei å dele bileta og videoane med andre om at dei opplev noko utanom det vanlege i kvardagen, og dei informantane deler med er i hovudsak vener og familie. Å dele bilete og videoar frå konsertane kan ha ein verdi ved at det opnar opp for at dei kan halde ved like eksisterande forhold og pleie nære relasjonar som informantane ikkje ser så ofte i kvardagen.

Find us

Lars Hilles gate 30
5008 Bergen
Norway

Contact us

MediaFutures
Office@mediafutures.no

 

Responsible Editor:
Centre Director Prof. Dr. Christoph Trattner
Christoph.Trattner@uib.no

NEWSLETTER

Subscribe to our monthly Newsletter by sending mail to office@mediafutures.no

 

Hosted by 

PARTNERS

CLUSTER

FUNDED BY

Copyright © University of Bergen 2024