User-controllable personalization
Denis Parra,Peter Brusilovsky +1 more
TL;DR: This research investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion, and introduced an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering.
read more
Abstract: In this research we investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion. We examined whether allowing the user to control the process of fusing or integrating different algorithms (i.e., different sources of relevance) resulted in increased engagement and a better user experience. The essential contribution of this research stems from the results of a user study (N=40) of controllability in a scenario where users could fuse different recommendation approaches, with the possibility of inspecting and filtering the items recommended. First, we introduce an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering. Second, we provide a three-fold evaluation of the user experience: objective metrics, subjective user perception, and behavioral measures. Through the analysis of these metrics, we confirmed results from recent studies, such as the effect of trusting propensity on accepting the recommendations and also unveiled the importance of features such as being a native speaker. Our results present several implications for the design and implementation of user-controllable personalized systems. We explored user-controllable interfaces as extension of traditional-ranked lists.We introduced SetFusion, a controllable interface with sliders and a Venn diagram.We conducted a controlled user study on online conference article recommendation.Our evaluation had three dimensions: users' perception, behavioral and IR metrics.Controllable interface had a positive effect influenced by users' characteristics.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Figure 12. Block model summarizes the statistical analysis conducted in the user study 
Table 4. List of actions tracked in the recommender interfaces (Controllable and Baseline). 
Figure 5. Workflow of user study. After answering the entry questionnaire (pre-survey), the subject was assigned to one of 2 possible sequences of interfaces: Non-controllable (No-C) and then controllable (C) interface, or vice versa. 
Figure 10. Average rating per recommender method (or overlaps of them) under the non-controllable and controllable interfaces. A is popularity based on bookmarks, B is the content-based recommender, and C is popularity based on authors’ citations. In overlaps, AB means papers recommended by both methods A and B. 
Figure 3. Screenshot of the sliders widget. The arrows highlight the actions that the user could perform in the controllable interface. 
Figure 2. Screenshot of the recommended items list. The arrows highlight the actions that the user can perform in the recommender interface.
Citations
Interactive recommender systems
TL;DR: An interactive visualization framework that combines recommendation with visualization techniques to support human-recommender interaction is presented and existing interactive recommender systems are analyzed along the dimensions of the framework.
343
•Proceedings Article
CHI '06 Extended Abstracts on Human Factors in Computing Systems
Gary M. Olson,Robin Jeffries +1 more
- 21 Apr 2006
TL;DR: This year's extended abstracts include submissions from six different sub-communities of the human-computer interaction field: design; education; engineering; management; research and usability, as well as materials from other traditional CHI venues.
184
Moodplay: Interactive music recommendation based on Artists’ mood similarity
TL;DR: MoodPlay is introduced, an interactive music-artists recommender system which integrates content and mood-based filtering in a novel interface which reveals the role of mood in music recommendation, considering both artists’ mood and users’ self-reported mood in the user study.
92
Exploring and Promoting Diagnostic Transparency and Explainability in Online Symptom Checkers
Chun-Hua Tsai,Yue You,Xinning Gui,Yubo Kou,John M. Carroll +4 more
- 06 May 2021
TL;DR: In this paper, a COVID-19 online symptom checker was enhanced with three types of explanations to enhance diagnostic transparency and improve user experience in high-stakes areas such as healthcare.
73
Controlling Spotify Recommendations: Effects of Personal Characteristics on Music Recommender User Interfaces
Martijn Millecamp,Nyi Nyi Htun,Yucheng Jin,Katrien Verbert +3 more
- 03 Jul 2018
TL;DR: Results indicate that the radar chart helped the participants discover a significantly higher number of new songs compared to the sliders, and it was found that users' experience with Spotify had an influence on their interaction with different musical attributes.
68
References
•Book
Introduction to Information Retrieval
Christopher D. Manning,Prabhakar Raghavan,Hinrich Schütze +2 more
- 01 Jan 2008
TL;DR: In this article, the authors present an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections.
•Book
Modern Information Retrieval
Ricardo Baeza-Yates,Berthier Ribeiro-Neto +1 more
- 15 May 1999
TL;DR: In this article, the authors present a rigorous and complete textbook for a first course on information retrieval from the computer science (as opposed to a user-centred) perspective, which provides an up-to-date student oriented treatment of the subject.
An Introduction to Information Retrieval
Stefano Ceri,Alessandro Bozzon,Marco Brambilla,Emanuele Della Valle,Piero Fraternali,Silvia Quarteroni +5 more
- 01 Jan 2013
TL;DR: This chapter introduces information retrieval as a scientific discipline, providing a formal characterization centered on the notion of relevance and touches on some of its challenges and classic applications and then dedicate a section to its main evaluation criteria: precision and recall.
6.9K
Evaluating collaborative filtering recommender systems
TL;DR: The key decisions in evaluating collaborative filtering recommender systems are reviewed: the user tasks being evaluated, the types of analysis and datasets being used, the ways in which prediction quality is measured, the evaluation of prediction attributes other than quality, and the user-based evaluation of the system as a whole.
GroupLens: an open architecture for collaborative filtering of netnews
Paul Resnick,Neophytos Iacovou,Mitesh Suchak,Peter Bergstrom,John Riedl +4 more
- 22 Oct 1994
TL;DR: GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles, and protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction.
6K