Enhanced Semantic Graph Based Approach With Sentiment Analysis For User Interest Retrieval From Social Sites
Usama Ahmed Jamal
TL;DR
The paper tackles extracting user interests from social-media text to enable targeted recommendations without relying on surveys or ratings. It introduces a semantic graph-based framework that uses Maui for keyword extraction, Zemanta with DBpedia for entity linking, and sentiment analysis to gauge opinion polarity, forming a keyword-based user-interest graph whose edges reflect semantic relatedness. By integrating product graphs and performing graph matching, the approach surfaces items that align with inferred user interests. This content-driven method aims to improve personalization at scale for social platforms, providing a more automated and semantically informed alternative to traditional survey- or history-based recommender systems.
Abstract
Blogs and social networking sites serve as a platform to the users for expressing their interests, ideas and thoughts. Targeted marketing uses the recommendation systems for suggesting their services and products to the users or clients. So the method used by target marketing is extraction of keywords and main topics from the user generated texts. Most of conventional methods involve identifying the personal interests just on the basis of surveys and rating systems. But the proposed research differs in manner that it aim at using the user generated text as a source medium for identifying and analyzing the personal interest as a knowledge base area of users. Semantic graph based approach is proposed research work that identifies the references of clients and users by analyzing their own texts such as tweets. The keywords need to be extracted from the text generated by the user on the social networking sites. This can be made possible by using several algorithms that extracts the keywords automatically from the available content provided by the user. Based on frequency and degree it ranks the extracted keywords. Furthermore, semantic graph based model assists in providing useful suggestions just by extracting the interests of users by analyzing their contents from social media. In this approach graph comprises of nodes and edges where nodes represents the keywords extracted by the algorithm and edges shows the semantic connection between the nodes. The method does not require internet related user activities like surveys or ratings to gather user interest related information.