BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//MediaFutures - ECPv6.15.13.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://mediafutures.no
X-WR-CALDESC:Events for MediaFutures
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Oslo
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20200329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20201025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20210328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20211031T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20221030T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20250404T140000
DTEND;TZID=Europe/Oslo:20250404T150000
DTSTAMP:20260420T075103
CREATED:20250321T152847Z
LAST-MODIFIED:20250402T133219Z
UID:20549-1743775200-1743778800@mediafutures.no
SUMMARY:Mid-term evaluation of PhD candidate Khadiga Seddik
DESCRIPTION:On Friday\, April 4th\, PhD candidate Khadiga Seddik will have her mid-term evaluation. \nMain supervisor: Erik Knudsen \nCo-Supervisor: Damian Trilling\, Alain Starke (Step-in) \nExternal Evaluator: Sole Pera \n\nTitle: The Influence of News Recommender technology on Shaping Selective Exposure and Sharing. \nAbstract:  \nDespite the benefits the news recommenders provide\, overly personalized news recommendations and too much exposure to like-minded news can pose a threat to democracy by leading to filter bubble\, echo-chambers\, and political polarization. These negative consequences are not given\, but they could depend on conditions and factors under which news recommenders amplify or reduce selective exposure. Many studies argue that news recommenders can be programmed to promote factors that reduce selective exposure because they are programmed by human beings\, and they are dependent on the decisions surrounding the implementation and design of the technology. However\, programming recommender systems to shape selective exposure is not a straightforward task\, as we don’t know which factors the recommenders should be designed to promote\, as well as how the recommenders should promote them. In this research project I investigate the heavily debated consequences of news recommender technologies\, selective exposure and selective of like-minded news. The aim is to shift the scholarly attention from uncovering whether the current recommenders amplify or reduce selective exposure to understanding the conditions under which recommender systems do so\, given that they are designed for that purpose. By doing so\, we shift the responsibility for the democratic implications of recommenders from the technology itself to the decisions surrounding the implementation and design. \nThe project is a part of a larger project\, the NEWSREC project (https://www.newsrec.ai). The main objective of NEWSREC project is to study\, understand\, and assess the precise conditions under which algorithmic news recommenders have positive or negative effects on the democratic role of the news media by focusing on both the input side and the output side of news recommenders.
URL:https://mediafutures.no/event/mid-term-evaluation-of-phd-candidate-khadiga-seddik/
LOCATION:SFI MediaFutures\, MCB
CATEGORIES:Events,WP1 Understanding Media Experiences,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/khadiga.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20250404T091500
DTEND;TZID=Europe/Oslo:20250404T101500
DTSTAMP:20260420T075103
CREATED:20250321T154003Z
LAST-MODIFIED:20250402T123002Z
UID:20553-1743758100-1743761700@mediafutures.no
SUMMARY:Mid-term evaluation of PhD candidate Jia-Hua Jeng
DESCRIPTION:On Friday\, April 4\, PhD candidate Jia-Hua Jeng will have his mid-term evaluation. \nMain supervisor: Christoph Trattner \nCo-Supervisors: Erik Knudsen\, Alain Starke \nExternal Evaluator: Sole Pera
URL:https://mediafutures.no/event/mid-term-evaluation-of-phd-candidate-jia-hua-jeng/
LOCATION:SFI MediaFutures\, MCB
CATEGORIES:Events,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/jeng.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20250403T153000
DTEND;TZID=Europe/Oslo:20250403T163000
DTSTAMP:20260420T075103
CREATED:20250321T152101Z
LAST-MODIFIED:20250402T133519Z
UID:20540-1743694200-1743697800@mediafutures.no
SUMMARY:Mid-term evaluation of PhD candidate Bilal Mahmood
DESCRIPTION:On Thursday\, April 3rd\, PhD candidate Bilal Mahmood will have his mid-term evaluation. \nMain supervisor: Mehdi Elahi \nCo-Supervisor: Samia Touileb \nExternal Evaluator: Sole Pera
URL:https://mediafutures.no/event/mid-term-evaluation-of-phd-candidate-bilal-mahmood/
LOCATION:SFI MediaFutures\, MCB
CATEGORIES:Events,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/bilal.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20240606T120000
DTEND;TZID=Europe/Oslo:20240606T130000
DTSTAMP:20260420T075103
CREATED:20240514T134153Z
LAST-MODIFIED:20240514T134153Z
UID:18212-1717675200-1717678800@mediafutures.no
SUMMARY:Transparency\, Privacy\, and Fairness in Recommender Systems
DESCRIPTION:MediaFutures has invited Dipl.Ing. Dr.techn. Dominik Kowald from Graz\, Austria to talk about transparency\, privacy and fairness in recommender systems. He is research area manager in Fair AI at the Know-Center and senior researcher and lecturer – ISDS (TU Graz). \nRecommender systems have become a pervasive part of our daily online experience by analyzing past usage behavior to suggest potential relevant content\, e.g.\, music\, movies\, or books. Today\, recommender systems are one of the most widely used applications of artificial intelligence and machine learning. Therefore\, regulations and requirements for trustworthy artificial intelligence\, for example\, the European AI Act\, which includes notions such as transparency\, privacy\, and fairness are also highly relevant for the design\, development\, evaluation\, and deployment of recommender systems in practice. \nThis talk elaborates on aspects related to these three notions in the light of recommender systems\, namely: (i) transparency and cognitive models\, (ii) privacy and limited preference information\, and (iii) fairness and popularity bias in recommender systems. Specifically\, with respect to aspect (i)\, I highlight the usefulness of incorporating psychological theories for a transparent design process of recommender systems. Additionally\, I show that cognitive models can further contribute to transparency aspects by illustrating how the models’ components have contributed to generate the recommendation lists. In aspect (ii)\, I study and address the trade-off between accuracy and privacy in differentially-private recommendations. \nDominic Kowald presents a novel recommendation approach for collaborative filtering based on an efficient neighborhood reuse concept\, which reduces the number of users that need to be protected with differential privacy. Furthermore\, he outlines the related issue of limited availability of user preference information\, e.g.\, click data\, in the settings of session-based recommendations\, by using variational autoencoders. With respect to aspect (iii)\, he discusses popularity bias in collaborative filtering-based recommender systems and shows that the recommendation frequency of an item is positively correlated with this item’s popularity. This also leads to the unfair treatment of users with little interest in popular content\, since these users receive worse recommendation accuracy results than users with high interest in popular content. Besides\, Kowald presents results of an online study on popularity bias mitigation in the field of news article recommendations. He closes the talk by illustrating the trade-off between privacy and popularity bias in recommender systems and by outlining future research possibilities in this direction. \nAfter the talk\, Kowald will present the Know-Center\, and some of their success stories and lessons learned of applied research projects with industry partners.
URL:https://mediafutures.no/event/transparency-privacy-and-fairness-in-recommender-systems/
LOCATION:MediaFutures\, Media Futures HQ\, 3rd floor\, Bergen\, 5008
CATEGORIES:Events,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/Frame-20-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20240405T130000
DTEND;TZID=Europe/Oslo:20240405T140000
DTSTAMP:20260420T075103
CREATED:20240308T141736Z
LAST-MODIFIED:20240315T134254Z
UID:17921-1712322000-1712325600@mediafutures.no
SUMMARY:News personalization with "Curate"
DESCRIPTION:MediaFutures invites to a seminar on news personalization with Schibsted in MediaFutures headquarter\, MCB\, 3rd floor. The seminar will also be streamed. \nThe Curate project has been created to enable Schibsted media outlets to craft an optimal content selection for each individual user\, delivering content tailored precisely to their preferences\, in the appropriate format\, location\, and timing\, all while upholding the journalistic integrity of the mission. Originally developed to curate Aftenposten’s front page in Norway\, Curate has evolved into the central recommendation system for over 50 news brands within the Schibsted and Polaris Media groups. \nChristoph Schmitz\, Product Manager of Curate and Jacob Welander\, Data Scientist at Schibsted will tell us in this seminar about the project itself\, what has been done so far and how Schibsted has been utilizing such technology innovating media experience. \nJoin the meeting on zoom:\nhttps://uib.zoom.us/j/69494993779?pwd=c0k3YXZ2MDduYnhoT2FUM09WNHNKdz09
URL:https://mediafutures.no/event/news-personalization-with-curate/
LOCATION:MediaFutures\, Media Futures HQ\, 3rd floor\, Bergen\, 5008
CATEGORIES:Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/png:https://mediafutures.no/wp-content/uploads/Frame-2-6.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20230414T133000
DTEND;TZID=Europe/Oslo:20230414T141500
DTSTAMP:20260420T075103
CREATED:20230331T123915Z
LAST-MODIFIED:20230417T073311Z
UID:14915-1681479000-1681481700@mediafutures.no
SUMMARY:MediaFutures Seminar: Computing Biases in Recommender Systems with Marko Tkalčič\, University of Primorska
DESCRIPTION:Marko Tkalčič from the University of Primorska in Koper\, Slovenia will give a seminar on April 14th. \nTITLE: Computational Psychology in Recommender Systems \nWHEN: 14 April\, 13:30 – 14:1  \n \nABSTRACT: \n\nRecommender systems are systems that help users in decision-making situations where there is an abundance of choices. We can find them in our everyday lives\, for example in online shops. State-of-the-art research in recommender systems has shown the benefits of behavioural modeling. Behavioural modeling means that we use past ratings\, purchases\, clicks etc. to model the user preferences. However\, behavioural modeling is not able to capture certain aspects of the user preferences. Behavioral modeling can amplify existing biases in datasets. In this talk I will show how the usage of complementary research in computational psychology\, such as detection of personality and emotions\, can help recommender systems to mitigate both data/algorithm biases and cognitive biases. \nBIO: \nMarko Tkalčič is associate professor at the Faculty of Mathematics\, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper\, Slovenia. He aims at improving personalized services (e.g. recommender systems) through the usage of psychological models in personalization algorithms. To achieve this\, he uses diverse research methodologies\, including data mining\, machine learning\, and user studies. He is editorial board member of the Springer UMUAI and Frontiers in Psychology journals and PC chair of the ACM UMAP 2021 conference.
URL:https://mediafutures.no/event/mediafutures-seminar-computational-psychology-in-recommender-systems-with-marko-tkalcic-university-of-primorska/
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/Marko-Tkalcic-e1625469689507.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20220421T130000
DTEND;TZID=Europe/Oslo:20220421T140000
DTSTAMP:20260420T075103
CREATED:20220331T190334Z
LAST-MODIFIED:20220424T153715Z
UID:11745-1650546000-1650549600@mediafutures.no
SUMMARY:MediaFutures Seminar: Fairness—Are algorithms a burden or a solution? Dr. Christine Bauer\, Assistant Professor at Utrecht University
DESCRIPTION:Dr. Christine Bauer\, Assistant Professor at Utrecht University\, will give a seminar on 21 April\, at 13:00. \nTITLE:  Fairness—Are algorithms a burden or a solution?WHEN: Thursday 21 April\, 13:00-14:00WHERE: Zoom – \nhttps://uib.zoom.us/j/66369080035?pwd=MDFzdmV6TUdCVVZlZnhsNWc1eHlMUT09  \nMeeting ID: 663 6908 0035\n\nPassword: F9fN181n\n \nABSTRACT: \nRecommender systems play an important role in everyday life. These systems assist users in choosing products to buy\, movies to watch\, or news articles to read. With their wide usage\, there is an increasing pressure that such systems are fair. Besides serving diverse groups of users\, recommenders need to represent and serve item providers in a fair manner\, too. But what is fair? In this talk\, I will present research on fairness in music recommender systems taking the artists’ perspective. What do artists consider fair? Are algorithms a burden or a solution? In particular\, I will zoom in on recent research on gender bias in music recommenders and how we can address this issue. \nBIO: \nDr. Christine Bauer is an Assistant Professor at Utrecht University\, The Netherlands. She is an experienced teacher in a wide spectrum of topics in computing and information systems—ranging from algorithms to adaptive interactive systems to research methods. Her research activities center on interactive intelligent systems. Thereby\, she takes a human-centered computing approach\, where technology follows humans’ and society’s needs. Central themes in her research are context and context-adaptivity.  In the recent years\, she worked on context-aware recommender systems. Core interest in her current research activities are fairness and multi-method evaluations. Further information can be found at https://christinebauer.eu.
URL:https://mediafutures.no/event/mediafutures-seminar-fairness-are-algorithms-a-burden-or-a-solution-dr-christine-bauer-assistant-professor-at-utrecht-university/
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/thumbnail_image001.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20220317T130000
DTEND;TZID=Europe/Oslo:20220317T140000
DTSTAMP:20260420T075104
CREATED:20220222T102109Z
LAST-MODIFIED:20220320T133719Z
UID:11451-1647522000-1647525600@mediafutures.no
SUMMARY:MediaFutures Seminar: Detecting Fake News by Using Weakly Supervised Learning. Assoc. Prof. Özlem Özgöbek
DESCRIPTION:Dr. Özlem Özgöbek\, Associate Professor at NTNU\, Norway will give a seminar on 17 March\, at 13:00. \nTITLE: Detecting Fake News by Using Weakly Supervised LearningWHEN: Thursday 17 March\, 13:00-14:00WHERE: Zoom – \nhttps://uib.zoom.us/j/64607939290?pwd=cStOdG90YWRjSW02RmN6TjAxakQwZz09 \nMeeting ID: 646 0793 9290\n\nPassword: m9hyue9C\n \nABSTRACT: \nSpread and existence of fake news has been amplified by the advancements in internet and social media. Today\, it is one of the most important problems that affects the society. Various artificial intelligence methods have been used to address the automatic detection of fake news. However\, the complex and dynamic nature of news makes this task challenging. In this talk\, I’m going to address some of these challenges and present an ongoing work on fake news detection by using weakly supervised learning. \nBIO: \nDr. Özlem Özgöbek works as an associate professor at the Department of Computer Science at NTNU. Her research focuses on recommender systems\, privacy issues in recommender systems and disinformation detection for online news. She is a co-founder of Norwegian Big Data Symposium (NOBIDS) and actively involved in organizing INRA workshop series since 2014.
URL:https://mediafutures.no/event/mediafutures-seminar-detecting-fake-news-by-using-weakly-supervised-learning-assoc-prof-ozlem-ozgobek/
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/NTNU.-dr.-Ozgobek.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20211125T120000
DTEND;TZID=Europe/Oslo:20211125T130000
DTSTAMP:20260420T075104
CREATED:20210916T123151Z
LAST-MODIFIED:20211129T065236Z
UID:9240-1637841600-1637845200@mediafutures.no
SUMMARY:MediaFutures Seminar: Translating Educational Data into Meaningful Practices: Insights from the field of Learning Analytics. Mohammad Khalil.
DESCRIPTION:Mohammad Khalil\, senior researcher at UiB Centre for the Science of Learning & Technology (SLATE)\, will give a seminar on 25 November\, at 12:00. \nTITLE: Translating Educational Data into Meaningful Practices: Insights from the field of Learning AnalyticsWHEN: Thursday 25 November\, 12:00-13:00WHERE: https://uib.zoom.us/j/63125529816?pwd=OTc0MStQYUczTkEzTXVRZTlBYUpyQT09Meeting ID: 631 2552 9816Password: 8U0vAVAy \nABSTRACT: \nSince the last decade\, higher education has moved online and institutions have had access to more student data than ever before. A proactive move before the recent pandemic where online and virtual learning environments had functioned as primarily digital repositories of educational resources\, employing student data to improve learning experiences and environments was disseminated in 2011\, so-called Learning Analytics. For 11 years\, the emerging of Learning Analytics has evolved into a mature research field and practice. \nIn this talk\, I will share with you some facts about the field in 4Ws\, Where it originates from? What theories have influenced the field? How does it translate students’ data into useful practices (empirical evidence)? and What concerns have been raised through such usage? \nBIO:Mohammad Khalil\, PhD\, is a senior researcher of Learning Analytics at the Centre for the Science of Learning & Technology (SLATE). His research interests focus on understanding online learning behavior based on students digital traces in virtual environments\, including self-regulation. His other research interests include privacy and ethics\, and visualizations. Khalil is the author of over 60 research papers in scholarly journals and international conferences in the area of Learning Analytics and Technology-Enhanced Learning.
URL:https://mediafutures.no/event/mediafutures-seminar-translating-educational-data-into-meaningful-practices-insights-from-the-field-of-learning-analytics-mohammad-khalil/
LOCATION:Online
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/Mohammad-Khalil.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20211028T120000
DTEND;TZID=Europe/Oslo:20211028T130000
DTSTAMP:20260420T075104
CREATED:20210916T121140Z
LAST-MODIFIED:20220225T081307Z
UID:9231-1635422400-1635426000@mediafutures.no
SUMMARY:MediaFutures Seminar: Countering rumours in online social media: A comprehensive response with the focus on ML-based approaches\, Amir Ebrahimi Fard
DESCRIPTION:Amir Ebrahimi Fard\, Postdoctoral Researcher on Explainable AI at Maastricht University\, will give a talk on Thursday 28 October\, at 12:00. \n  \nTITLE: Countering rumours in online social media: A comprehensive response with the focus on ML-based approachesWHEN: Thursday 28 October 2021\, 12:00-13:00WHERE: Zoom: https://uib.zoom.us/j/62501981715?pwd=cTFaemd6d2gzWTVlamcrWW9BTC8rdz09 Meeting ID: 625 0198 1715Password: MQFY5Zm1 \nAbstract:  \nThe phenomenon of rumour spreading refers to a collective process where people participate in the transmission of unverified and relevant information to make sense of ambiguous\, dangerous\, or threatening situations. The dissemination of rumours in certain subject domains such as healthcare\, economics\, and politics on a large scale no matter with what purpose could precipitate catastrophic repercussions. Thus it is of utmost importance to respond to this growing threat urgently and meticulously. There have been serious efforts by governments\, platforms\, news organisations\, and academic institutions around the world to curb and control the dissemination of online rumours; however\, the surge of unsubstantiated claims and conspiracy theories during the COVID time showed the power of this phenomenon once more. \nInspired by epidemiology\, during this seminar\, I will discuss a comprehensive and coordinated response to counter rumour spreading in social media. Besides\, in this response\, I will emphasise the role of machine learning-based models due to their scalability and point out one specific issue with current approaches to computational rumour detection. \nBio:  \nAmir Ebrahimi Fard is a postdoctoral researcher on Explainable AI at the Department of Data Science and Knowledge Engineering at Maastricht University. He received his PhD from TU Delft on the topic of rumour detection in online social media.
URL:https://mediafutures.no/event/mediafutures-seminar-amir-ebrahimi-fard/
LOCATION:Online
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/photo_Amir-Ebrahimi-Fard-scaled-e1636031008101.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20210608T110000
DTEND;TZID=Europe/Oslo:20210608T120000
DTSTAMP:20260420T075104
CREATED:20210519T132514Z
LAST-MODIFIED:20210705T072001Z
UID:5663-1623150000-1623153600@mediafutures.no
SUMMARY:Seminar: Computational Psychology in Recommender Systems\, Marko Tkalčič\, University of Primorska (Slovenia).
DESCRIPTION:MediaFutures is pleased to announce that Marko Tkalčič\, who is an Associate Professor at University of Primorska (Slovenia) will be giving a seminar on the topic of computational psychology in recommender systems. \nWelcome to all! \nTITLE: Computational Psychology in Recommender Systems\nWHEN: Tuesday\, 8 June 2021\, at 11:00-12:00\nWHERE: https://uib.zoom.us/j/61489174500?pwd=MGRQWWs2K0lYQ1hPSlBJZjF5VU85Zz09\nMeeting ID: 614 8917 4500\nPassword: 27A9wUG6 \nABSTRACT: Recommender systems are systems that help users in decision-making situations where there is an abundance of choices. We can find them in our everyday lives\, for example in online shops. State-of-the-art research in recommender systems has shown the benefits of behavioural modeling. Behavioural modeling means that we use past ratings\, purchases\, clicks etc. to model the user preferences. However\, behavioural modeling is not able to capture certain aspects of the user preferences. In this talk I will show how the usage of complementary research in computational psychology\, such as detection of personality and emotions\, can benefit recommender systems. \nBIO: Marko Tkalčič is associate professor at the Faculty of Mathematics\, Natural Sciences and Information Technologies (FAMNIT) at the University of Primorska in Koper\, Slovenia. He aims at improving personalized services (e.g. recommender systems) through the usage of psychological models in personalization algorithms. To achieve this\, he uses diverse research methodologies\, including data mining\, machine learning\, and user studies. He is editorial board member of the Springer UMUAI and Frontiers in Psychology journals and PC chair of the ACM UMAP 2021 conference. \n 
URL:https://mediafutures.no/event/seminar-computational-psychology-in-recommender-systems-marko-tkalcic-university-of-primorska-slovenia/
LOCATION:Online
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/Marko-Tkalcic-e1625469689507.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20210506T141500
DTEND;TZID=Europe/Oslo:20210506T150000
DTSTAMP:20260420T075104
CREATED:20210416T123518Z
LAST-MODIFIED:20210713T100852Z
UID:5570-1620310500-1620313200@mediafutures.no
SUMMARY:Seminar: User-centered Investigation of Popularity Bias in Recommender Systems
DESCRIPTION:Please join the Center for Data Science (CEDAS\, UiB) and MediaFutures for an invited talk by Himan Abdollahpouri from the Northwestern University\, USA\, about the topic of popularity bias in recommender systems. \nWelcome to all! \n\nTITLE: User-centered Investigation of Popularity Bias in Recommender Systems.\nWHEN: 6 May 2021\, 14:15-15:00\nWHERE: https://uib.zoom.us/j/63657771765?pwd=anZlNkVPdkxoQ0FmZit5WDJ0R3FkQT09 \nABSTRACT: Recommendation and ranking systems are known to suffer from popularity bias; the tendency of the algorithm to favor a few popular items while under-representing the majority of other items. Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail\, less popular\, items. The effectiveness of these approaches is often assessed using different metrics to evaluate the extent to which over-concentration on popular items is reduced. However\, not much attention has been given to the user-centered evaluation of this bias; how different users with different levels of interest towards popular items (e.g.\, niche vs blockbuster-focused users) are affected by such algorithms. In this talk\, I first give an overview of the popularity bias problem in recommender systems. Then\, I show the limitations of the existing metrics to evaluate popularity bias mitigation when we want to assess these algorithms from the users’ perspective and I propose a new metric that can address these limitations. In addition\, I present an effective approach that mitigates popularity bias from the user-centered point of view. Finally\, I investigate several state-of-the-art approaches proposed in recent years to mitigate popularity bias and evaluate their performances using the existing metrics and also from the users’ perspective. Using two publicly available datasets\, I show that many of the existing popularity bias mitigation techniques ignore the users’ tolerance towards popular items. The proposed user-centered method\, on the other hand\, can tackle popularity bias effectively for different users while also improving the existing metrics. \nBIO: Himan Abdollahpouri is a Postdoctoral Fellow at the Spiegel Research Center at Northwestern University\, USA. He received his Ph.D. in Information Science at the University of Colorado Boulder under the supervision of Prof. Robin Burke. He was a pioneer in developing the multi-stakeholder recommendation research paradigm and has worked on the biases that might jeopardize the fairness of the recommendations across different stakeholders. In particular\, he has done extensive work on the popularity bias in recommender systems and proposed several algorithms and evaluation metrics in this area. His work has appeared in top conferences such as RecSys\, CIKM\, UMAP\, and journals such as UMUAI. He also has worked at Pandora Media and Spotify Research as a machine learning scientist.
URL:https://mediafutures.no/event/seminar-user-centered-investigation-of-popularity-bias-in-recommender-systems/
LOCATION:Online
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/himan_abdollahpouri-e1626170916223.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Oslo:20210420T140000
DTEND;TZID=Europe/Oslo:20210420T150000
DTSTAMP:20260420T075104
CREATED:20210322T072825Z
LAST-MODIFIED:20210430T120902Z
UID:5369-1618927200-1618930800@mediafutures.no
SUMMARY:Seminar: Reflections of Ourselves - Mobile Psychological Assessment with Smartphones. Clemens Stachl\, Stanford University
DESCRIPTION:MediaFutures is pleased to announce a seminar with Clemens Stachl from Stanford University. The video recording is available below. \nWelcome to all! \nTITLE: Reflections of Ourselves – Mobile Psychological Assessment with Smartphones.\nWHEN: 20 April 2021\, 14:00-15:00. \n \nABSTRACT: The increasing digitization of our society radically changes how we use digital media\, exchange information\, and make decisions. This development also changes how social scientists collect data on human behavior and experience in the field. One new form of data comes from in-vivo high-frequency mobile sensing via smartphones. Mobile sensing allows for the investigation of formerly intangible psychological constructs with objective data. In particular mobile sensing enables fine-grained\, longitudinal data collections in the wild and at large scale. The additional combination of mobile sensing with state of the art machine learning methods\, provides a perspective for the direct prediction of psychological traits and behavioral outcomes from these data. In this talk I will give an overview on my work combining machine learning with mobile sensing and discuss the opportunities and limitations of this approach. Consequently\, I will provide an outlook perspective on where the routine use of mobile psychological sensing could take research and society alike. \nBIO: Clemens Stachl is a post-doctoral researcher specializing in research methodology\, behavioral observation and individual differences. His research includes topics in psychology\, artificial intelligence and human-computer interaction. He primarily uses digital recordings from consumer electronics together with computational modeling to investigate the connections between psychological characteristics\, states\, behavior and situational factors. Throughout his work he promotes open scientific practices.
URL:https://mediafutures.no/event/seminar-reflections-of-ourselves-mobile-psychological-assessment-with-smartphones-with-clemens-stachl-stanford-university/
LOCATION:Online
CATEGORIES:Events,Seminar,WP2 User Modeling, Personalisation & Engagement
ATTACH;FMTTYPE=image/jpeg:https://mediafutures.no/wp-content/uploads/Clemens-Stachl-e1625469908417.jpg
END:VEVENT
END:VCALENDAR