User Profiling in Social Networks

Please enable javascript in your browser.

Ketabchi, Mohammad Amin | 2021

794 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53852 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Sameti, Hossein
Abstract:
Due to the emergence of social networks in recent years and people’s usage of them for expressing their thoughts and emotions, there are lots of user data in these networks. The development of social networks has created a good opportunity for organizations and people to extract user profiles from social networks. Hence, user profiling has become an interesting problem for researchers. Predicting users’ occupational class is one of the main problems in this field. Most of the existing related works use only textual features of users, whereas users’ relations graph can give useful information about users. In this research, we propose a model based on Graph Neural Networks (GNNs) to predict users’ occupational class using both textual and graph features. The results of testing the proposed model on a standard dataset - consisting of users’ occupational class on Twitter - and comparing it with previous related works shows that the proposed model can improve the accuracy of prediction from 52% (the best result of previous works) to more than 60%
Keywords:
Social Networks ; Graph Neural Network ; Occupational Class Prediction ; User Profiling ; Twitter Social Network