Diversity has been an important concept in both interactive information retrieval (IIR) and recommendation systems (RS), especially in the context of entertainment activities such as music, video, or games.However, diversity itself is a highly abstract concept, and providing diversity to users brings the risk of unsatisfactory results.In this short paper, we investigate diversity in the context of music recommendation.We conducted an online survey with 149 participants to investigate how they perceive music diversity.Our results revealed their explicit ideas about different aspects of diversity, as well as their underlying perceptions shaping their diversity preferences.We propose viewing music diversity using an "above and below-surface" structure, and our findings can help design other entertainment systems such as video or games.

Generative AI (GenAI) technologies such as ChatGPT are changing the ways people interact with information.To illustrate, popular search engines (e.g., Google) have started integrating responses from GenAI tools with the traditional search results.In this paper, we explore the integration of GenAI technology with traditional search in the context of a learning-oriented task.We report on a between-subjects study (𝑁 = 40) in which participants completed a complex, learning-oriented search task.Participants were assigned to one of two conditions.In the SearchOnly condition, participants used a traditional web search system to gather information.In the Search+Chat condition, participants used an experimental system that combined a traditional web search component and an interactive GenAI-based chat component (Chat AI).The study investigated seven research questions.RQ1-RQ3 focused on differences between groups: (RQ1) post-task perceptions, (RQ2) search behaviors, and (RQ3) learning outcomes.To measure learning, participants completed a multiple-choice test before the search task, immediately after, and one week later (to measure retention).RQ4-RQ7 delved deeper into participants' behaviors and experiences in the Search+Chat condition: (RQ4) motivations for (and gains from) engaging with the Chat AI; (RQ5) the phases during which participants engaged with the Chat AI; (RQ6) the types of queries issued to each component; and (RQ7) perceptions about the information returned by each component.

Music listening is heavily influenced by contexts, and contextual factors can shape users’ interaction with music information retrieval (MIR) systems. To better design context-sensitive user experiences in MIR systems, in this paper, we present a review of prior studies on how contexts are associated with user behavior in MIR systems. Contextual factors considered include interaction design, age, personality, time of day, activity, motivation, nationality, etc. Based on the review, we introduce a framework to consider these contextual factors in a consistent and organized way. The framework is adapted from Ingwersen and Järvelin’s 2006 nested contexts framework, and has four layers: 1) MIR/system contexts that focus on MIR systems themselves, including both hardware and software; 2) situational contexts that describe varied and transient daily situations where users interact with MIR systems; 3) personal contexts that focus on the more stable personal characteristics; and 4) social and cultural contexts that describe the characteristics of users’ environments. We also present an example to illustrate how to systematically analyze user contexts by using the framework. Finally, we discuss several areas for possible future studies.