Taketoshi Ushiama

Sosui Moribe, Taketoshi Ushiama

Serendipity-oriented recommender systems expose users to unfamiliar items to counter filter bubbles, yet mere exposure does not ensure that users will understand or appreciate the content they encounter. We propose Peer Recommendation, a framework in which a user and an AI agent (Peer) with distinct preferences collaboratively explore unfamiliar content. Unlike conventional conversational recommender systems where the user is a passive recipient, our framework positions the user as both a recommender and a recipient: the user and the Peer mutually recommend songs to each other through chat-based dialogue, collaboratively building a shared playlist. In an exploratory within-subjects experiment (N=14), we compared three conditions: (1) a Close Peer, (2) a Distant Peer, and (3) a baseline agent without an explicit preference profile. The Close Peer significantly increased users' interest expansion and perceived value of the activity compared to the baseline, with medium-to-large effect sizes. The Distant Peer showed no significant difference at the aggregate level; however, qualitative analysis revealed varied responses, with some participants strongly preferring the Distant Peer. These findings suggest that the "otherness" of a recommendation partner is essential for moving beyond mere exposure toward genuine engagement, and that the appropriate degree of preference distance may vary and need to be adapted to individual users.

Teruki Nakahara, Taketoshi Ushiama

When reading news articles on social networking services and news sites, readers can view comments marked by other people on these articles. By reading these comments, a reader can understand the public opinion about the news, and it is often helpful to grasp the overall picture of the news. However, these comments often contain offensive language that readers do not prefer to read. This study aims to predict such offensive comments to improve the quality of the experience of the reader while reading comments. By considering the diversity of the readers' values, the proposed method predicts offensive news comments for each reader based on the feedback from a small number of news comments that the reader rated as "offensive" in the past. In addition, we used a machine learning model that considers the characteristics of the commenters to make predictions, independent of the words and topics in news comments. The experimental results of the proposed method show that prediction can be personalized even when the amount of readers' feedback data used in the prediction is limited. In particular, the proposed method, which considers the commenters' characteristics, has a low probability of false detection of offensive comments.

Sosui Moribe, Taketoshi Ushiama

In recent years, peer learning has gained attention as a method that promotes spontaneous thinking among learners, and its effectiveness has been confirmed by numerous studies. This study aims to develop an AI Agent as a learning companion that enables peer learning anytime and anywhere. However, peer learning between humans has various limitations, and it is not always effective. Effective peer learning requires companions at the same proficiency levels. In this study, we assume that a learner's peers with the same proficiency level as the learner make the same mistakes as the learner does and focus on English composition as a specific example to validate this approach.