رسائل دكتوراة
French
2021
Social information retrieval: A Hybrid Approach Based on Analysis and Information Extraction
Chaa Messaoud , باتريس بلوط, نوالي عمر
كلية العلوم الدقيقة-جامعة عبد الرحمان ميرة - بجاية · الجزائر
The emergence of social media has revolutionized the Web, notably by allowing users to interact,exchange messages and share their knowledge with other users in the form of comments, annotations andratings of resources. These tasks have led to a dramatic growth of information on the web. This newinformation, known as social information, has been a source of evidence, in the field of social informationresearch, for estimating the relevance of documents and better responding to user requests. However, the useof social information to improve information retrieval has several challenges, the most important of which are(i) find a better representation of documents taking into account the social dimension, (ii) adapt the models ofinformation retrieval to take into account the different types of social information such as comments andannotations, (iii) find a better representation of the user request which is generally complex and formulated innatural language in social forums. The main contributions of our work consist in proposing an approach basedon reduction and expansion to process natural language queries and better understand user needs. We alsopropose to adapt and parametrize the IR models to suit the different types of social information. Finally, inorder to better exploit users' reviews, we propose a new representation of documents, which combines termsand features extracted from user reviews. The proposed approaches were evaluated on two datasets, SocialBook Search and App Retrieval, and the results clearly show the improvement in search performance.