This chapter gives an overview of the area of explanations in recommender systems. We approach the literature from the angle of evaluation: that is, we are interested in what makes an explanation “good”. The chapter starts by describing how explanations can be affected by how recommendations are presented, and the role the interaction with the recommender system plays w.r.t. Explanations. Next, we introduce a number of explanation styles on three levels focusing on the individual user, contextualization, and self-actualization. In this section, we also discuss how the explanation style can be related to the underlying algorithms. We identify benefits that explanations may contribute to a recommender system, and relate them to criteria used in evaluations of explanations in existing systems, and how these relate to evaluations with existing recommender systems. A number of factors influence how effective explanations are, such as personal and situational characteristics, and we dedicate a section to these emerging findings as well. We conclude the chapter with open research questions and future work, including current recommender systems topics such as social recommendations (e.g., for groups), explanations to deal with bias; sets and sequences; and over- and under reliance. Examples of explanations in existing systems are mentioned throughout.
|Title of host publication||Recommender Systems Handbook|
|Editors||Francescho Ricci, Lior Rokach, Bracha Shapira, Paul B. Kantor|
|Publication status||Published - 2022|