Abstract
This work presents a concept featuring interactive explanations for mobile shopping recommender systems in the domain of fashion. It combines previous research in explanations in recommender systems and critiquing systems. It is tailored to a modern smartphone platform, exploits the benefits of the mobile environment and incorporates a touchbased interface for convenient user input. Explanations have the potential to be more conversational when the user can change the system behavior by interacting with them. However, in traditional recommender systems, explanations are used for one-way communication only. We therefore design a system, which generates personalized interactive explanations using the current state of the user's inferred preferences and the mobile context. An Android application was developed and evaluated by following the proposed concept. The application proved itself to outperform the previous version without interactive and personalized explanations in terms of transparency, scrutability, perceived effciency and user acceptance.
| Original language | English |
|---|---|
| Pages (from-to) | 14-21 |
| Number of pages | 8 |
| Journal | CEUR Workshop Proceedings |
| Volume | 1253 |
| State | Published - 2014 |
| Event | Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, IntRS 2014, Co-located with ACM Conference on Recommender Systems, RecSys 2014 - Foster City, United States Duration: 6 Oct 2014 → … |
Keywords
- Active Learning
- Content-based
- Explanations
- Mobile recommender systems
- Scrutability
- User interaction