@article{ubo_mods_00204805, author = {Hernandez-Bocanegra, Diana C. and Ziegler, Jürgen}, title = {Explaining Recommendations through Conversations: Dialog Model and the Effects of Interface Type and Degree of Interactivity}, journal = {ACM Transactions on Interactive Intelligent Systems (TiiS)}, year = {2023}, publisher = {Association for Computing Machinery (ACM)}, address = {New York}, volume = {13}, number = {2}, keywords = {Recommender systems; explanations; argumentation; interactive interfaces; conversational agent; dataset; intent detection; user study}, issn = {2160-6455}, doi = {10.1145/3579541}, url = {https://doi.org/10.1145/3579541}, note = {001018513000001}, language = {en} } @inproceedings{ubo_mods_00181315, author = {Hellmann, Marco and Hernandez Bocanegra, Diana and Ziegler, Jürgen}, editor = {Smith-Renner, Alison and Amir, Ofra}, title = {Development of an Instrument for Measuring Users’ Perception of Transparency in Recommender Systems}, booktitle = {Workshops at the International Conference on Intelligent User Interfaces (IUI) 2022: Proceedings of the IUI 2022 Workshops: APEx-UI, HAI-GEN, HEALTHI, HUMANIZE, TExSS, SOCIALIZE}, series = {CEUR Workshop Proceedings}, year = {2022}, publisher = {RWTH Aachen}, address = {Aachen}, volume = {3124}, pages = {156–165}, keywords = {Recommender systems}, abstract = {Transparency is increasingly seen as a critical requirement for achieving the goal of human-centered AI systems in general and also, specifically, recommender systems (RS). However, defining and operationalizing the concept is still difficult, due to its multi-faceted nature. Currently, there are hardly any measurement instruments to adequately assess the perceived transparency of RS in user studies. Thus, we present the development of a measurement instrument that aims at capturing perceived transparency as a multidimensional construct. The results of our validation show that transparency can be distinguished with respect to input (what data does the system use?), functionality (how and why is an item recommended?), output (why and how well does an item fit one’s preferences?), and interaction (what needs to be changed for a different prediction?). The study is intended as a first iteration in the development of a reliable and fully validated measurement tool for assessing transparency in RS.}, issn = {1613-0073}, doi = {10.17185/duepublico/75905}, url = {https://doi.org/10.17185/duepublico/75905}, language = {en} } @phdthesis{ubo_mods_00181111, author = {Hernandez Bocanegra, Diana Carolina}, title = {Argumentative Explanations for Recommendations Based on Reviews}, year = {2022}, address = {Duisburg, Essen}, keywords = {Recommender systems, Explanations, Argumentation, Interactive interfaces design, Conversational agent, Dataset, Empirical studies}, abstract = {Recommender systems (RS) assist users in making decisions on a wide range of tasks, while preventing them from being overwhelmed by enormous amounts of choices. RS prevalence is such that many users of information-based technologies interact with them on a daily basis. However, many of these systems are still perceived as black boxes by users, who often have no way of seeing or requesting the reasons why certain items are recommended, potentially leading to negative attitudes towards RS by users. Providing explanations in RS can bring several advantages for users’ decision making and overall user experience. Although different explanatory approaches have been proposed so far, the general lack of user evaluation, and validation of concepts and implementations of explainable methods in RS, have left open many questions, related to how such explanations should be structured and presented. Also, while explanations in RS have so far been presented mostly in a static and non-interactive manner, limited work in explainable artificial intelligence have emerged addressing interactive explanations, enabling users to examine in detail system decisions. However, little is known about how interactive interfaces in RS should be conceptualized and designed, so that explanatory aims such as transparency and trust are met. This dissertation investigates interactive, conversational explanations that enable users to freely explore explanatory content at will. Our work is grounded on RS explainable methods that exploit user reviews, and inspired by dialog models and formal argument structures. Following a user-centered approach, this dissertation proposes an interface design for explanations as interactive argumentation, which was empirically validated through different user studies. To this end, we implemented a RS able to provide explanations both through a graphical user interface (GUI) navigation and a natural language interface. The latter consists of a conversational agent for explainable RS, which supports conversation flows for different types of questions written by users in their own words. To this end, we formulated a model to facilitate the detection of the intent expressed by a user on a question, and collected and annotated a dataset helpful for intent detection, which can facilitate the development of explanatory dialog systems in RS. The results reported in this dissertation indicate that providing interactive explanations through a conversation, i.e. an exchange of questions and answers between the user and the system, using both GUI-navigation or natural language conversation, can positively impact users evaluation of explanation quality and of the system, in terms of explanatory aims like transparency, and trust.}, school = {University of Duisburg-Essen}, doi = {10.17185/duepublico/75833}, url = {https://doi.org/10.17185/duepublico/75833} } @inproceedings{ubo_mods_00168064, author = {Hernandez-Bocanegra, Diana Carolina and Ziegler, Jürgen}, title = {ConvEx-DS: A Dataset for Conversational Explanations in Recommender Systems}, booktitle = {Interfaces and Human Decision Making for Recommender Systems 2021: Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems}, series = {CEUR Workshop Proceedings}, year = {2021}, publisher = {CEUR-WS}, address = {Aachen}, volume = {2948}, pages = {3–20}, keywords = {Conversational agent; Dataset; Explanations; Recommender systems; User study}, issn = {1613-0073}, language = {en} } @inproceedings{ubo_mods_00167903, author = {Hernandez Bocanegra, Diana Carolina and Ziegler, Jürgen}, editor = {Ardito, Carmelo and Lanzilotti, Rosa and Malizia, Alessio and Petrie, Helen and Piccinno, Antonio and Desolda, Giuseppe and Inkpen, Kori}, title = {Effects of Interactivity and Presentation on Review-Based Explanations for Recommendations}, booktitle = {Human-Computer Interaction – INTERACT 2021: Proceedings, Part II}, series = {Lecture Notes in Computer Science}, year = {2021}, publisher = {Springer}, address = {Cham}, volume = {12933}, pages = {597–618}, keywords = {Explanations; Interactivity; Recommender systems; User characteristics; User study}, abstract = {User reviews have become an important source for recommending and explaining products or services. Particularly, providing explanations based on user reviews may improve users’ perception of a recommender system (RS). However, little is known about how review-based explanations can be effectively and efficiently presented to users of RS. We investigate the potential of interactive explanations in review-based RS in the domain of hotels, and propose an explanation scheme inspired by dialogue models and formal argument structures. Additionally, we also address the combined effect of interactivity and different presentation styles (i.e. using only text, a bar chart or a table), as well as the influence that different user characteristics might have on users’ perception of the system and its explanations. To such effect, we implemented a review-based RS using a matrix factorization explanatory method, and conducted a user study. Our results show that providing more interactive explanations in review-based RS has a significant positive influence on the perception of explanation quality, effectiveness and trust in the system by users, and that user characteristics such as rational decision-making style and social awareness also have a significant influence on this perception.}, isbn = {978-3-030-85615-1}, doi = {10.1007/978-3-030-85616-8_35}, url = {https://doi.org/10.1007/978-3-030-85616-8_35}, language = {en} } @inproceedings{ubo_mods_00167074, author = {Hernandez-Bocanegra, Diana C. and Ziegler, Jürgen}, title = {Conversational Review-based Explanations for Recommender Systems: Exploring Users’ Query Behavior}, booktitle = {CUI 2021 - 3rd Conference on Conversational User Interfaces}, series = {ACM International Conference Proceeding Series}, year = {2021}, publisher = {Association for Computing Machinery (ACM)}, address = {New York}, keywords = {argumentation; conversational agent; explanations; Recommender systems; user study}, abstract = {Providing explanations based on user reviews in recommender systems (RS) can increase users’ perception of system transparency. While static explanations are dominant, interactive explanatory approaches have emerged in explainable artificial intelligence (XAI), so that users are more likely to examine system decisions and get more arguments supporting system assertions. However, little attention has been paid to conversational approaches for explanations targeting end users. In this paper we explore how to design a conversational interface to provide explanations in a review-based RS, and present the results of a Wizard of Oz (WoOz) study that provided insights into the type of questions users might ask in such a context, as well as their perception of a system simulating such a dialog. Consequently, we propose a dialog management policy and user intents for explainable review-based RS, taking as an example the hotels domain.}, isbn = {9781450389983}, doi = {10.1145/3469595.3469596}, url = {https://dl.acm.org/doi/10.1145/3469595.3469596?cid=99659550942}, language = {en} } @inproceedings{ubo_mods_00166665, author = {Hernandez Bocanegra, Diana Carolina and Borchert, Angela and Brünker, Felix and Shahi, Gautam Kishore and Ross, Björn}, title = {Towards a Better Understanding of Online Influence: Differences in Twitter Communication Between Companies and Influencers}, booktitle = {ACIS 2020 Proceedings}, series = {ACIS 2020 Proceedings}, year = {2020}, volume = {18}, keywords = {Online influence}, abstract = {In the last decade, Social Media platforms such as Twitter have gained importance in the various marketing strategies of companies. This work aims to examine the presence of influential content on a textual level, by investigating characteristics of tweets in the context of social impact theory, and its dimension immediacy. To this end, we analysed influential Twitter communication data during Black Friday 2018 with methods from social media analytics such as sentiment analysis and degree centrality. Results show significant differences in communication style between companies and influencers. Companies published longer textual content and created more tweets with a positive sentiment and more first-person pronouns than influencers. These findings shall serve as a basis for a future experimental study to examine the impact of text presence on consumer cognition and the willingness to purchase.}, url = {https://aisel.aisnet.org/acis2020/18/}, language = {en} } @inproceedings{ubo_mods_00166661, author = {Hernandez Bocanegra, Diana Carolina and Ziegler, Jürgen}, editor = {Hansen, C. and Nürnberger, A. and Preim, B.}, title = {Argumentative explanations for recommendations - Effect of display style and profile transparency}, booktitle = {Mensch und Computer 2020}, year = {2020}, keywords = {Recommender systems, explanations, user study}, abstract = {Providing explanations based on user reviews in recommender systems may increase users’ perception of transparency. However, little is known about how these explanations should be presented to users in order to increase both their understanding and acceptance. We present in this paper a user study to investigate the effect of different display styles (visual and text only) on the perception of review-based explanations for recommended hotels. Additionally, we also aim to test the differences in users’ perception when providing information about their own profiles, in addition to a summarized view on the opinions of other users about the recommended hotel. Our results suggest that the perception of explanations regarding these aspects may vary depending on user characteristics, such as decision-making styles or social awareness.}, doi = {10.18420/muc2020-ws111-338}, url = {https://doi.org/10.18420/muc2020-ws111-338}, language = {en} } @article{ubo_mods_00161373, author = {Hernandez-Bocanegra, Diana C. and Ziegler, Jürgen}, title = {Explaining Review-Based Recommendations: Effects of Profile Transparency, Presentation Style and User Characteristics}, journal = {i-com: Journal of Interactive Media}, year = {2020}, publisher = {de Gruyter}, address = {Berlin}, volume = {19}, number = {3}, pages = {181–200}, keywords = {user study}, abstract = {Providing explanations based on user reviews in recommender systems (RS) may increase users’ perception of transparency or effectiveness. However, little is known about how these explanations should be presented to users, or which types of user interface components should be included in explanations, in order to increase both their comprehensibility and acceptance. To investigate such matters, we conducted two experiments and evaluated the differences in users’ perception when providing information about their own profiles, in addition to a summarized view on the opinions of other customers about the recommended hotel. Additionally, we also aimed to test the effect of different display styles (bar chart and table) on the perception of review-based explanations for recommended hotels, as well as how useful users find different explanatory interface components. Our results suggest that the perception of an RS and its explanations given profile transparency and different presentation styles, may vary depending on individual differences on user characteristics, such as decision-making styles, social awareness, or visualization familiarity.}, issn = {2196-6826}, doi = {10.1515/icom-2020-0021} } @inproceedings{ubo_mods_00154786, author = {Hernandez-Bocanegra, Diana C. and Donkers, Tim and Ziegler, Jürgen}, title = {Effects of Argumentative Explanation Types on the Perception of Review-Based Recommendations}, booktitle = {Adjunct Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’20 Adjunct)}, year = {2020}, publisher = {Association for Computing Machinery (ACM)}, address = {New York}, pages = {219–225}, keywords = {user study}, abstract = {Recommender systems have achieved considerable maturity and accuracy in recent years. However, the rationale behind recommendations mostly remains opaque. Providing textual explanations based on user reviews may increase users’ perception of transparency and, by that, overall system satisfaction. However, little is known about how these explanations can be effectively and efficiently presented to the user. In the following paper, we present an empirical study conducted in the domain of hotels to investigate the effect of different textual explanation types on, among others, perceived system transparency and trustworthiness, as well as the overall assessment of explanation quality. The explanations presented to participants follow an argument-based design, which we propose to provide a rationale to support a recommendation in a structured way. Our results show that people prefer explanations that include an aggregation using percentages of other users’ opinions, over explanations that only include a brief summary of opinions. The results additionally indicate that user characteristics such as social awareness may influence the perception of explanation quality.}, isbn = {9781450367110}, doi = {10.1145/3386392.3399302}, url = {https://dl.acm.org/doi/10.1145/3386392.3399302?cid=99659550942} }