Research Article
Prediction Method of Consumption Behaviour on Social Network Oriented to User Mental Model
@INPROCEEDINGS{10.1007/978-3-031-28867-8_39, author={Han Yin}, title={Prediction Method of Consumption Behaviour on Social Network Oriented to User Mental Model}, proceedings={Advanced Hybrid Information Processing. 6th EAI International Conference, ADHIP 2022, Changsha, China, September 29-30, 2022, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2023}, month={3}, keywords={User mental model Social network Consumption behavior Behavior prediction Subdivision ensemble learning model}, doi={10.1007/978-3-031-28867-8_39} }- Han Yin
Year: 2023
Prediction Method of Consumption Behaviour on Social Network Oriented to User Mental Model
ADHIP PART 2
Springer
DOI: 10.1007/978-3-031-28867-8_39
Abstract
The current consumption behavior prediction method is mainly to use historical data modeling, through finding the laws of the data, to predict the user's consumption behavior. But the consumption psychology of users in social network will be impacted by the information in social network. The current usage methods ignore the impact of users’ psychology on consumption behavior. In order to improve the above defects, the prediction method of social network consumption behavior oriented to user mental model is studied. Psychological characteristics refer to the stable characteristics of psychological activities. After understanding the psychological characteristics of users, the user's social network consumption psychological model is established. Dynamic identification is performed according to the user's personal preferences. According to the fit between user preferences and commodity characteristics, the utility value of commodities is obtained, and the social network consumption behavior is predicted using the differentiation ensemble learning model. The experimental results show that the average prediction accuracy is up to 90.52%, about 15% higher than the original method, and the proposed method has good stability for different conditions.
