GR/AP Interactive Explanations for Sequence Recommendation in Travel and Tourism

Recommender systems recommend movies, restaurants or other items to an active user based on information about users and items. The domain of travel and tourism is more complex than others because the context (time, location) plays a larger role, and often, several items need to be combined for a composite recommendation. Consider the following scenario: a tourist exploring a city wants a personalized walking tour combining several points-of-interests to a reasonable sequence. In this and many other scenarios, it is not only important to recommend the best items but explain why they are recommended to users. Explanations or justification in recommender systems are well-studied for individual items (see [1] for a recent and comprehensive overview), but not necessarily for sequences of items (see Section 6.4 in [1] for a few approaches).

The goal in this Guided Research in the Informatics (or related) Master’s program (IN2169) or Application Project in the Master Data Engineering and Analytics program (IN2328) is to investigate interactive explanations for sequence recommendation in travel and tourism in more detail. The main idea is to not only consider explanations for single items or a whole sequence, but focus on the transition and relation of items in the sequence. Examples may include "Walking from the museum to the restaurant is recommended because it is a nice short walk" or "Restaurant after museum is recommended because this sequence is preferred".

The proposed course of action is as follows:

• Overview of the state-of-the-art in the explained specific research area
• Designing a solution and implementing a prototype to allow test users to interact with an application (but no backend or actual recommender system needed)
• Conducting a user study to evaluate the approach

The project has to be documented in a brief scientific report that can possibly be submitted to a conference or workshop. The interaction prototype can be developed in any mobile platform, e.g. Web-based or mobile. Prerequisites are high motivation and good programming skills in the selected platform. Please send your application (brief CV, transcript of records, and short motivation statement) to Wolfgang Wörndl (woerndl@cit.tum.de) until March 14th. (Decision and possible start soon after this date, with registration by the first week of the new semester.)

[1] Tintarev, N., Masthoff, J. (2022). Beyond Explaining Single Item Recommendations. In: Ricci, F., Rokach, L., Shapira, B. (eds) Recommender Systems Handbook. Springer, New York, NY. https://doi.org/10.1007/978-1-0716-2197-4_19