AG 1, AG 2, INET, AG 4, AG 5, D6, SWS, RG1   Info

Public Audience

English

60 Minutes

Saarbrücken

Search-based recommendation is a paradigm that combines users’ long-term profiles with their current search queries to guide the recommendation process. This dissertation investigates how user-generated text can serve as a valuable source for constructing textual user profiles, with an emphasis on transparency and scrutability, enabling users to understand and control their profiles. It makes three key contributions:
(1) demonstrating the effectiveness of sparse, questionnaire-based profiles for capturing core preferences;

(2) leveraging user-to-user chat data as a novel, richer profiling source; and
(3) developing methods to distill concise profiles from long, noisy review texts using a range of techniques.

Petra Schaaf

+49 681 9325 5000

--email hidden

Zoom

678 2346 9165

passcode not visible

logged in users only