Harnessing user’s social influence and IoT data for personalized event recommendation in event-based social networks

Autor: Pratibha Mahajan, Pankaj Deep Kaur
Rok vydání: 2021
Předmět:
Zdroj: Social Network Analysis and Mining. 11
ISSN: 1869-5469
1869-5450
DOI: 10.1007/s13278-021-00722-6
Popis: With the popularization of Internet, newly emerged event-based social networks (EBSNs) have experienced recognition among people for planning, scheduling, and communicating social events. Due to plethora of events occurring over EBSNs and varying user interests and preferences with time, finding appropriate events to attend has become an important challenge in EBSNs. Accurate event recommendation will improve relevance of ESBNs to participants and event organizers. EBSNs have recognized the importance of recommender systems and are actively using different types of recommendation techniques to make suitable suggestions to participants and organizers of events. In this paper, a novel event recommendation system (i.e., IoTCFR- IoT data and collaborative filtering-based recommendation) is proposed. In order to suggest an event where the chance of user’s participation is high, the proposed approach combines IoT data, collaborative filtering (CF) approach, and social influence. Initially, the prediction score for both IoT-based parameters and CF based on social influencers is calculated for each candidate event. Then, the final event with highest prediction score is presented to the user. Furthermore, in order to verify the accuracy of proposed system, several experiments on real-world datasets were conducted. The results clearly indicate that recommendation quality of IoTCFR system is better, when compared to its variants and other baseline methods.
Databáze: OpenAIRE
Externí odkaz: