@inproceedings{ubo_mods_00148660,
  author = {Donkers, Tim and Kleemann, Timm and Ziegler, Jürgen},
  editor = {Paternò, Fabio and Oliver, Nuria},
  title = {Explaining Recommendations by Means of Aspect-Based Transparent Memories},
  booktitle = {Proceedings of the 25th International Conference on Intelligent User Interfaces},
  year = {2020},
  publisher = {The Association for Computing Machinery},
  address = {New York, NY},
  pages = {166–176},
  isbn = {978-1-4503-7118-6},
  doi = {10.1145/3377325.3377520},
  url = {https://dl.acm.org/doi/pdf/10.1145/3377325.3377520},
  abstract = {Recommender Systems have seen substantial progress in terms of algorithmic sophistication recently. Yet, the systems mostly act as black boxes and are limited in their capacity to explain why an item is recommended. In many cases recommendations methods are employed in scenarios where users not only rate items, but also convey their opinion on various relevant aspects, for instance by the means of textual reviews. Such user-generated content can serve as a useful source for deriving explanatory information to increase system intelligibility and, thereby, the user’s understanding.
 We propose a recommendation and explanation method that exploits the comprehensiveness of textual data to make the underlying criteria and mechanisms that lead to a recommendation more transparent. Concretely, the method incorporates neural memories that store aspect-related opinions extracted from raw review data. We apply attention mechanisms to transparently write and read information from memory slots.
 Besides customary offline experiments, we conducted an extensive user study. The results indicate that our approach achieves a higher overall quality of explanations compared to a state-of-the-art baseline. Utilizing Structural Equation Modeling, we additionally reveal three linked key factors that constitute explanation quality: Content adequacy, presentation adequacy, and linguistic adequacy.}
}


@inproceedings{ubo_mods_00089097,
  author = {Feuerbach, Jan and Loepp, Benedikt and Barbu, Catalin-Mihai and Ziegler, Jürgen},
  title = {Enhancing an Interactive Recommendation System with Review-based Information Filtering},
  booktitle = {Proceedings of the 4th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS ’17)},
  series = {CEUR workshop proceedings},
  year = {2017},
  volume = {1884},
  pages = {2–9},
  keywords = {User Reviews},
  abstract = {Integrating interactive faceted filtering with intelligent recommendation techniques has shown to be a promising means for increasing user control in Recommender Systems. In this paper, we extend the concept of blended recommending by automatically extracting meaningful facets from social media by means of Natural Language Processing. Concretely, we allow users to influence the recommendations by selecting facet values and weighting them based on information other users provided in their reviews. We conducted a user study with an interactive recommender implemented in the hotel domain. This evaluation shows that users are consequently able to find items fitting interests that are typically difficult to take into account when only structured content data is available. For instance, the extracted facets representing the opinions of hotel visitors make it possible to effectively search for hotels with comfortable beds or that are located in quiet surroundings without having to read the user reviews.},
  url = {http://ceur-ws.org/Vol-1884/paper1.pdf}
}


@inproceedings{ubo:72486,
  author = {Barbu, Catalin-Mihai},
  chapter = {},
  title = {Increasing the Trustworthiness of Recommendations by Exploiting Social Media Sources},
  year = {2016},
  address = {New York, NY, USA},
  publisher = {ACM},
  pages = {447–450},
  keywords = {recommender systems},
  abstract = {Current recommender systems mostly do not take into account as well as they might the wealth of information available in social media, thus preventing the user from obtaining a broad and reliable overview of different opinions and ratings on a product. Furthermore, there is a lack of user control over the recommendation process–which is mostly fully automated and does not allow the user to influence the sources and mechanisms by which recommendations are produced–as well as over the presentation of recommended items. Consequently, recommendations are often not transparent to the user, are considered to be less trustworthy, or do not meet the user’s situational needs. This work will investigate the theoretical foundations for user-controllable, interactive methods of recommending, will develop techniques that exploit social media data in conjunction with other sources, and will validate the research empirically in the area of e-commerce product recommendations. The methods developed are intended to be applicable in a wide range of recommending and decision support scenarios.},
  isbn = {978-1-4503-4035-9},
  doi = {10.1145/2959100.2959104},
  url = {https://dl.acm.org/citation.cfm?id=2959104},
  booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems}
}