Home // ACHI 2020, The Thirteenth International Conference on Advances in Computer-Human Interactions // View article

A Fuzzy Logic Approach for Dynamic User Interests Profiling

Authors:
Abd El Heq Silem
Hajer Taktak
Faouzi Moussa

Keywords: Context-Awareness; Fuzzy Logic; Fuzzy Logic System; User Profiling; User Behavior.

Abstract:
The user profile is the virtual representation of the user that holds a variety of user information such as personal data, interests, preferences, and environment. In literature, there are two different techniques for profiling user interests. The first one is based on the retrieval of text from the user browsing history; this technique has a high probability to generate a false interest from uninteresting websites. The second technique is based on user behavior (factors like scrolling speed or time spent) and navigation history. The proposed approach using the second technique does not use enough factors and calculates the weight of each factor via predefined ranges, which is not accurate for all users. This technique generates incorrect factor weight and false user interests. In this paper, we propose an approach that employs Fuzzy Logic with several factors (scrolling speed, time spent, and the number of visits) to automatically build and update the user profile from the user's browsing history. The target websites for this approach are websites that contain text content rather than visual content. This approach adapts the range of each factor according to the user habits using Fuzzy Logic, which improves accuracy and avoids a predefined factor range. Finally, we use an ontology-based model to store the user profile.

Pages: 317 to 323

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-761-0

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020