Evaluating the Effectiveness of A Suggested Architecture for The Real-Time Social Recommendation System
Rania Albalawi, Tet Hin Yeap, Morad Benyoucef · 2021
With the growth of social media and online network sites, a large number of textual data are continuously generated every day, however, it is a challenging subject to detect, describe and analyze those unstructured and semi-structured textual data since it has the characteristics of interactivity, sociality, and real-time means. Consequently, researchers have proposed several data mining methods that are used for building effective social recommendation systems to enhance user commercial and social activities. In this paper, we evaluated the performance of our developed real-time social recommendation system called ChatWithRec that aims to analyze the user's contextual conversation dynamically, detect the topic, and then match it with a suitable advertisement to increase the accuracy of recommendations. In our evaluation, we utilized a set of textual datasets to test the conversational analysis segment by using a modified Latent Dirichlet Allocation topic modeling method. Besides, we involved Google's Mobile ad network and an adjusted advertisement database (considering only some fields which are, food and travel subjects including booking hotels and flight adverts) as a task-related output action to collect qualitative data and defining the user's behaviors within-subjects' interaction with our system. The results are encouraging and indicate that the system is fast, satisfy users by getting what they seek without interrupting their conversation flow.