FFM-SVD: A Novel Approach for Personality-aware Recommender Systems
- Resource Type
- Conference
- Authors
- Widdeson, Kai; Hadzidedic, Suncica
- Source
- 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA) Computer Systems and Applications (AICCSA), 2022 IEEE/ACS 19th International Conference on. :1-8 Dec, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Dictionaries
Taxonomy
Neural networks
Predictive models
Data models
Recommender systems
Tuning
recommender systems
machine learning
personality
context-aware recommendations
- Language
- ISSN
- 2161-5330
This paper addresses and evaluates approaches to incorporating personality data into a recommender system. Automatic personality recognition is enabled by the LIWC dictionary. Personality-aware pre-filtering techniques are developed and discussed, with the introduced non-targeted stratified personality sampling performing the best. A novel personality-aware model, FFM-SVD, is proposed and shown to outperform alternative models in prediction accuracy.