GR User Interfaces for Travel Recommender Systems

Recommender systems recommend movies, restaurants or other items to an active user based on information about users and items. Research in this area does not only have to consider the underlying algorithms, but also how users interact with the systems. The user Interaction is mostly concerned with submitting initial preferences and giving feedback to suggested items.

The domain of travel and tourism is more complex than others, because the products to be recommended have many facets and need to be combined for a composite or packaged trip. Existing solutions often allow to specify basic parameters such as time frame and budget, select pre-defined activities such as hiking or culture, and rate recommended trips on a 5-star scale, but the user interface to do this often is very limited and not really tailored for these tasks.

The goal in this Guided Research project for the Informatics Master’s program (IN2169) is to investigate improved solutions for user interaction in travel recommendation for preference elicitation and/or user feedback. The actual focus can be discussed and will be specific, you are welcomed to propose own ideas, options include:

- Comparing different methods for preference elicitation, e.g. questionnaire with features vs. pairwise comparison of pictures
- Investigating the trade-off between controllability (e.g. showing more features and options) and cognitive load
- User interface issues in the decision making process of users, e.g. whether how to present recommended items does change the users' choice satisfaction
- Comparing different methods for user feedback on recommended items, e.g. rating-based vs. critiquing items

The proposed course of action is as follows:

* Overview of the state-of-the-art, both in existing applications and also research literature (e.g. [1] is a starting point)
* Designing a solution, which can be very focused but should include some novel aspect(s)
* Implementing a prototype to allow test users to interact with the system (but no backend or actual recommender system needed)
* Conducting a user study using an appropriate method, comparing the proposed solution(s) with a baseline

The interaction prototype can be developed in any platform, e.g. Web-based or as a mobile application. Prerequisites are high motivation and good enough programming skills in the selected platform. Please send your application (brief CV, transcript of records and short motivation statement, optionally already including the platform you may want to base your prototype on) to Wolfgang Wörndl (woerndl@in.tum.de). The start of the project is flexible, but a guided research module has to be formally registered in the first week of the semester.

[1] M. Jugovac, D. Jannach: Interacting with Recommenders - Overview and Research Directions. ACM Transactions on Interactive Intelligent Systems (TiiS), 7 (3), 2017