Authors:
Ahmed Galal
and
Abeer El-Korany
Affiliation:
Cairo University, Egypt
Keyword(s):
Dynamic User Modeling, Social Networks, Similarity Measurement, Topical Interest, User Behavior.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Enterprise Information Systems
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Society, e-Business and e-Government
;
Software Agents and Internet Computing
;
Symbolic Systems
;
User Profiling and Recommender Systems
;
Web 2.0 and Social Networking Controls
;
Web Information Systems and Technologies
Abstract:
Social Networks are popular platforms for users to express themselves, facilitate interactions, and share knowledge. Today, users in social networks have personalized profiles that contain their dynamic attributes representing their interest and behavior over time such as published content, and location check-ins. Several proposed models emerged that analyze those profiles with their dynamic content in order to measure the degree of similarity between users. This similarity value can be further used in friend suggesting and link prediction. The main drawback of the majority of these models is that they rely on a static snapshot of attributes which do not reflect the change in user interest and behavior over time. In this paper a novel framework for modeling the dynamic of user’s behavior and measuring the similarity between users’ profiles in twitter is proposed. In this proposed framework, dynamic attributes such as topical interests and the associated locations in tweets are used t
o represent user’s interest and behavior respectively. Experiments on a real dataset from twitter showed that the proposed framework that utilizes those attributes outperformed multiple standard models that utilize a static snapshot of data.
(More)