2021
|
Jannach, Dietmar; Jesse, Mathias; Jugovac, Michael; Trattner, Christoph Exploring Multi-List User Interfaces for Similar-Item Recommendations Conference 29th ACM International Conference on User Modeling, Adaptation and Personalization (UMAP '21) 2021. Abstract | Links | BibTeX @conference{Jannach2021,
title = {Exploring Multi-List User Interfaces for Similar-Item Recommendations},
author = {Dietmar Jannach and Mathias Jesse and Michael Jugovac and Christoph Trattner},
url = {https://mediafutures.no/conference_umap_2021-2/},
year = {2021},
date = {2021-03-26},
organization = {29th ACM International Conference on User Modeling, Adaptation and Personalization (UMAP '21)},
abstract = {On many e-commerce and media streaming sites, the user inter-face (UI) consists of multiple lists of item suggestions. The itemsin each list are usually chosen based on pre-defined strategies and,e.g., show movies of the same genre or category. Such interfacesare common in practice, but there is almost no academic researchregarding the optimal design and arrangement of such multi-listUIs for recommenders. In this paper, we report the results of anexploratory user study that examined the effects of various designalternatives on the decision-making behavior of users in the con-text of similar-item recommendations. Our investigations showed,among other aspects, that decision-making is slower and more de-manding with multi-list interfaces, but that users also explore moreoptions before making a decision. Regarding the selection of thealgorithm to retrieve similar items, our study furthermore revealsthe importance of considering social-based similarity measures.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
On many e-commerce and media streaming sites, the user inter-face (UI) consists of multiple lists of item suggestions. The itemsin each list are usually chosen based on pre-defined strategies and,e.g., show movies of the same genre or category. Such interfacesare common in practice, but there is almost no academic researchregarding the optimal design and arrangement of such multi-listUIs for recommenders. In this paper, we report the results of anexploratory user study that examined the effects of various designalternatives on the decision-making behavior of users in the con-text of similar-item recommendations. Our investigations showed,among other aspects, that decision-making is slower and more de-manding with multi-list interfaces, but that users also explore moreoptions before making a decision. Regarding the selection of thealgorithm to retrieve similar items, our study furthermore revealsthe importance of considering social-based similarity measures. |
2019
|
Trattner, Christoph; Jannach, Dietmar Learning to Recommend Similar Items from Human Judgements Journal Article User Modeling and User-Adapted Interaction Journal, pp. 1-50, 2019, (Pre SFI). Abstract | Links | BibTeX @article{Trattner2020,
title = {Learning to Recommend Similar Items from Human Judgements},
author = {Christoph Trattner and Dietmar Jannach},
url = {https://www.christophtrattner.info/pubs/UMUAI2019.pdf},
doi = {10.1007/s11257-019-09245-4},
year = {2019},
date = {2019-09-20},
journal = {User Modeling and User-Adapted Interaction Journal},
pages = {1-50},
abstract = {Similar item recommendations—a common feature of many Web sites—point users to other interesting objects given a currently inspected item. A common way of computing such recommendations is to use a similarity function, which expresses how much alike two given objects are. Such similarity functions are usually designed based on the specifics of the given application domain. In this work, we explore how such functions can be learned from human judgments of similarities between objects, using two domains of “quality and taste”—cooking recipe and movie recommendation—as guiding scenarios. In our approach, we first collect a few thousand pairwise similarity assessments with the help of crowdworkers. Using these data, we then train different machine learning models that can be used as similarity functions to compare objects. Offline analyses reveal for both application domains that models that combine different types of item characteristics are the best predictors for human-perceived similarity. To further validate the usefulness of the learned models, we conducted additional user studies. In these studies, we exposed participants to similar item recommendations using a set of models that were trained with different feature subsets. The results showed that the combined models that exhibited the best offline prediction performance led to the highest user-perceived similarity, but also to recommendations that were considered useful by the participants, thus confirming the feasibility of our approach.},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Similar item recommendations—a common feature of many Web sites—point users to other interesting objects given a currently inspected item. A common way of computing such recommendations is to use a similarity function, which expresses how much alike two given objects are. Such similarity functions are usually designed based on the specifics of the given application domain. In this work, we explore how such functions can be learned from human judgments of similarities between objects, using two domains of “quality and taste”—cooking recipe and movie recommendation—as guiding scenarios. In our approach, we first collect a few thousand pairwise similarity assessments with the help of crowdworkers. Using these data, we then train different machine learning models that can be used as similarity functions to compare objects. Offline analyses reveal for both application domains that models that combine different types of item characteristics are the best predictors for human-perceived similarity. To further validate the usefulness of the learned models, we conducted additional user studies. In these studies, we exposed participants to similar item recommendations using a set of models that were trained with different feature subsets. The results showed that the combined models that exhibited the best offline prediction performance led to the highest user-perceived similarity, but also to recommendations that were considered useful by the participants, thus confirming the feasibility of our approach. |
2018
|
Ocaña, Marc Gallofré; Nyre, Lars; Opdahl, Andreas Lothe; Tessem, Bjørnar; Trattner, Christoph; Veres, Csaba Towards a big data platform for news angles Workshop Norwegian Big Data Symposium 2018, 2018, (Pre SFI). Abstract | Links | BibTeX @workshop{Ocaña2018,
title = {Towards a big data platform for news angles},
author = {Marc Gallofré Ocaña and Lars Nyre and Andreas Lothe Opdahl and Bjørnar Tessem and Christoph Trattner and Csaba Veres},
url = {https://www.researchgate.net/publication/332274562_Towards_a_Big_Data_Platform_for_News_Angles},
year = {2018},
date = {2018-11-01},
booktitle = {Norwegian Big Data Symposium 2018},
abstract = {Finding good angles on news events is a central journalistic and editorial skill. As news work becomes increasingly computer-assisted and big-data based, journalistic tools therefore need to become better able to support news angles too. This paper outlines a big-data platform that is able to suggest appropriate angles on news events to journalists. We first clarify and discuss the central characteristics of news angles. We then proceed to outline a big-data architecture that can propose news angles. Important areas for further work include: representing news angles formally; identifying interesting and unexpected angles on unfolding events; and designing a big-data architecture that works on a global scale.
},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
Finding good angles on news events is a central journalistic and editorial skill. As news work becomes increasingly computer-assisted and big-data based, journalistic tools therefore need to become better able to support news angles too. This paper outlines a big-data platform that is able to suggest appropriate angles on news events to journalists. We first clarify and discuss the central characteristics of news angles. We then proceed to outline a big-data architecture that can propose news angles. Important areas for further work include: representing news angles formally; identifying interesting and unexpected angles on unfolding events; and designing a big-data architecture that works on a global scale.
|
Sciascio, Cecilia Di; Brusilovsky, Peter; Trattner, Christoph; Veas, Eduardo The Roadmap to User-Controllable Social Exploratory Search Journal Article ACM Transactions on Interactive Intelligent Systems, pp. 1-37, 2018, (Pre SFI). Abstract | Links | BibTeX @article{Sciascio2018,
title = {The Roadmap to User-Controllable Social Exploratory Search},
author = {Cecilia Di Sciascio and Peter Brusilovsky and Christoph Trattner and Eduardo Veas},
url = {https://www.christophtrattner.info/pubs/TIIS2019.pdf},
year = {2018},
date = {2018-01-01},
journal = {ACM Transactions on Interactive Intelligent Systems},
pages = {1-37},
abstract = {Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory
search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial-and-error
and on-the-!y selections, gathers and organizes information (resources). A range of innovative interfaces
with increased user control have been developed to support exploratory search process. In this work we
present our attempt to increase the power of exploratory search interfaces by using ideas of social search,
i.e., leveraging information left by past users of information systems. Social search technologies are highly
popular nowadays, especially for improving ranking. However, current approaches to social ranking do not
allow users to decide to what extent social information should be taken into account for result ranking. This
paper presents an interface that integrates social search functionality into an exploratory search system in
a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates
control features that allow the user to (i) express information needs by selecting keywords and (ii) to express
preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes
search transparency through color-coded stacked bars and rich tooltips. This work presents the full series
of evaluations conducted to, "rst, assess the value of the social models in contexts independent to the user
interface, in terms of objective and perceived accuracy. Then, in a study with the full-!edged system, we
investigated system accuracy and subjective aspects with a structural model that revealed that, when users
actively interacted with all its control features, the hybrid system outperformed a baseline content-based-only
tool and users were more satis"ed.},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory
search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial-and-error
and on-the-!y selections, gathers and organizes information (resources). A range of innovative interfaces
with increased user control have been developed to support exploratory search process. In this work we
present our attempt to increase the power of exploratory search interfaces by using ideas of social search,
i.e., leveraging information left by past users of information systems. Social search technologies are highly
popular nowadays, especially for improving ranking. However, current approaches to social ranking do not
allow users to decide to what extent social information should be taken into account for result ranking. This
paper presents an interface that integrates social search functionality into an exploratory search system in
a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates
control features that allow the user to (i) express information needs by selecting keywords and (ii) to express
preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes
search transparency through color-coded stacked bars and rich tooltips. This work presents the full series
of evaluations conducted to, "rst, assess the value of the social models in contexts independent to the user
interface, in terms of objective and perceived accuracy. Then, in a study with the full-!edged system, we
investigated system accuracy and subjective aspects with a structural model that revealed that, when users
actively interacted with all its control features, the hybrid system outperformed a baseline content-based-only
tool and users were more satis"ed. |
2017
|
Elsweiler, David; Trattner, Christoph; Harvey, Morgan Exploiting Food Choice Biases for Healthier Recipe Recommendation Conference ACM SIGIR Conference 2017, (Pre SFI). Abstract | Links | BibTeX @conference{Elsweiler2017,
title = {Exploiting Food Choice Biases for Healthier Recipe Recommendation},
author = {David Elsweiler and Christoph Trattner and Morgan Harvey},
url = {https://www.christophtrattner.info/pubs/SIGIR2017.pdf},
year = {2017},
date = {2017-08-01},
organization = {ACM SIGIR Conference},
abstract = {By incorporating healthiness into the food recommendation / ranking
process we have the potential to improve the eating habits of a
growing number of people who use the Internet as a source of food
inspiration. In this paper, using insights gained from various data
sources, we explore the feasibility of substituting meals that would
typically be recommended to users with similar, healthier dishes.
First, by analysing a recipe collection sourced from Allrecipes.com,
we quantify the potential for nding replacement recipes, which are
comparable but have di erent nutritional characteristics and are
nevertheless highly rated by users. Building on this, we present two
controlled user studies (n=107, n=111) investigating how people
perceive and select recipes. We show participants are unable to
reliably identify which recipe contains most fat due to their answers
being biased by lack of information, misleading cues and limited
nutritional knowledge on their part. By applying machine learning
techniques to predict the preferred recipes, good performance can
be achieved using low-level image features and recipe meta-data as
predictors. Despite not being able to consciously determine which
of two recipes contains most fat, on average, participants select
the recipe with the most fat as their preference. The importance of
image features reveals that recipe choices are often visually driven.
A nal user study (n=138) investigates to what extent the predictive
models can be used to select recipe replacements such that users
can be “nudged” towards choosing healthier recipes. Our ndings
have important implications for online food systems.},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
By incorporating healthiness into the food recommendation / ranking
process we have the potential to improve the eating habits of a
growing number of people who use the Internet as a source of food
inspiration. In this paper, using insights gained from various data
sources, we explore the feasibility of substituting meals that would
typically be recommended to users with similar, healthier dishes.
First, by analysing a recipe collection sourced from Allrecipes.com,
we quantify the potential for nding replacement recipes, which are
comparable but have di erent nutritional characteristics and are
nevertheless highly rated by users. Building on this, we present two
controlled user studies (n=107, n=111) investigating how people
perceive and select recipes. We show participants are unable to
reliably identify which recipe contains most fat due to their answers
being biased by lack of information, misleading cues and limited
nutritional knowledge on their part. By applying machine learning
techniques to predict the preferred recipes, good performance can
be achieved using low-level image features and recipe meta-data as
predictors. Despite not being able to consciously determine which
of two recipes contains most fat, on average, participants select
the recipe with the most fat as their preference. The importance of
image features reveals that recipe choices are often visually driven.
A nal user study (n=138) investigates to what extent the predictive
models can be used to select recipe replacements such that users
can be “nudged” towards choosing healthier recipes. Our ndings
have important implications for online food systems. |
Elahi, Mehdi; Hosseini, Reza; Rimaz, Mohammad H; Moghaddam, Farshad B; Trattner, Christoph Visually-Aware Video Recommendation in the Cold Start Conference Proccedings of theACM Hypertext 2020 2017, (Pre SFI). Abstract | Links | BibTeX @conference{Elahi2017b,
title = {Visually-Aware Video Recommendation in the Cold Start},
author = {Mehdi Elahi and Reza Hosseini and Mohammad H. Rimaz and Farshad B. Moghaddam and Christoph Trattner},
url = {https://christophtrattner.com/pubs/ht2020.pdf},
year = {2017},
date = {2017-07-01},
pages = {1-5},
organization = {Proccedings of theACM Hypertext 2020},
abstract = {Recommender Systems (RSs) have become essential tools in any
video-sharing platforms (such as YouTube) by generating video
suggestions for users. Although, RSs have been e!ective, however,
they su!er from the so-called New Item problem. New item problem,
as part of Cold Start problem, happens when a new item is added to
the system catalogue and the RS has no or little data available for
that new item. In such a case, the system may fail to meaningfully
recommend the new item to any user.
In this paper, we propose a novel recommendation technique
based on visual tags, i.e., tags that are automatically annotated
to videos based on visual description of videos. Such visual tags
can be used in an extreme cold start situation, where neither any
rating, nor any tag is available for the new video item. The visual
tags could also be used in the moderate cold start situation when
the new video item has been annotated with few tags. This type
of content features can be extracted automatically without any
human involvement and have been shown to be very e!ective in
representing the video content.
We have used a large dataset of videos and shown that automatically
extracted visual tags can be incorporated into the cold start
recommendation process and achieve superior results compared to
the recommendation based on human-annotated tags.},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Recommender Systems (RSs) have become essential tools in any
video-sharing platforms (such as YouTube) by generating video
suggestions for users. Although, RSs have been e!ective, however,
they su!er from the so-called New Item problem. New item problem,
as part of Cold Start problem, happens when a new item is added to
the system catalogue and the RS has no or little data available for
that new item. In such a case, the system may fail to meaningfully
recommend the new item to any user.
In this paper, we propose a novel recommendation technique
based on visual tags, i.e., tags that are automatically annotated
to videos based on visual description of videos. Such visual tags
can be used in an extreme cold start situation, where neither any
rating, nor any tag is available for the new video item. The visual
tags could also be used in the moderate cold start situation when
the new video item has been annotated with few tags. This type
of content features can be extracted automatically without any
human involvement and have been shown to be very e!ective in
representing the video content.
We have used a large dataset of videos and shown that automatically
extracted visual tags can be incorporated into the cold start
recommendation process and achieve superior results compared to
the recommendation based on human-annotated tags. |
2016
|
Mutlu, Belgin; Veas, Eduardo; Trattner, Christoph VizRec: Recommending Personalized Visualizations Journal Article ACM Transactions on Interactive Intelligent Systems (TiiS), 6 (4), pp. 1-40, 2016, (Pre SFI). Abstract | Links | BibTeX @article{Mutlu2016,
title = {VizRec: Recommending Personalized Visualizations},
author = {Belgin Mutlu and Eduardo Veas and Christoph Trattner},
url = {https://www.christophtrattner.info/pubs/ACM-TIIS.pdf},
year = {2016},
date = {2016-01-01},
journal = {ACM Transactions on Interactive Intelligent Systems (TiiS)},
volume = {6},
number = {4},
pages = {1-40},
abstract = {Visualizations have a distinctive advantage when dealing with the information overload problem: since they
are grounded in basic visual cognition, many people understand them. However, creating the appropriate
representation requires specific expertise of the domain and underlying data. Our quest in this paper is to
study methods to suggest appropriate visualizations autonomously. To be appropriate, a visualization has
to follow studied guidelines to find and distinguish patterns visually, and encode data therein. Thus, a
visualization tells a story of the underlying data; yet, to be appropriate, it has to clearly represent those aspects
of the data the viewer is interested in. Which aspects of a visualization are important to the viewer? Can
we capture and use those aspects to recommend visualizations? This paper investigates strategies to
recommend visualizations considering different aspects of user preferences. A multi-dimensional scale is used to
estimate aspects of quality for charts for collaborative filtering. Alternatively, tag vectors describing charts
are used to recommend potentially interesting charts based on content. Finally, a hybrid approach combines
information on what a chart is about (tags) and how good it is (ratings). We present the design principles
behind VizRec, our visual recommender. We describe its architecture, the data acquisition approach with a
crowd sourced study, and the analysis of strategies for visualization recommendation.},
note = {Pre SFI},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Visualizations have a distinctive advantage when dealing with the information overload problem: since they
are grounded in basic visual cognition, many people understand them. However, creating the appropriate
representation requires specific expertise of the domain and underlying data. Our quest in this paper is to
study methods to suggest appropriate visualizations autonomously. To be appropriate, a visualization has
to follow studied guidelines to find and distinguish patterns visually, and encode data therein. Thus, a
visualization tells a story of the underlying data; yet, to be appropriate, it has to clearly represent those aspects
of the data the viewer is interested in. Which aspects of a visualization are important to the viewer? Can
we capture and use those aspects to recommend visualizations? This paper investigates strategies to
recommend visualizations considering different aspects of user preferences. A multi-dimensional scale is used to
estimate aspects of quality for charts for collaborative filtering. Alternatively, tag vectors describing charts
are used to recommend potentially interesting charts based on content. Finally, a hybrid approach combines
information on what a chart is about (tags) and how good it is (ratings). We present the design principles
behind VizRec, our visual recommender. We describe its architecture, the data acquisition approach with a
crowd sourced study, and the analysis of strategies for visualization recommendation. |
