Semantic Term-Term Coupling-Based Feature Enhancement of User Profiles in Recommendation Systems

Mona Tanwar,Ravi Pendse,Sunil Kumar Khatri

doi:10.4018/jcit.20220701.oa1

Abstract

Content-based recommender system is a subclass of information systems that recommends an item to the user based on its description. It suggests items such as news, documents, articles, webpages, journals, and more to users as per their inclination by comparing the key features of the items with key terms or features of user interest profiles. This paper proposes the new methodology using Non-IIDness based semantic term-term coupling from the content referred by users to enhance recommendation results. In the proposed methodology, the semantic relationship is analyzed by estimating the explicit and implicit relationship between terms. It associates terms that are semantically related in real world or are used inter-changeably such as synonyms. The underestimated features of user profiles have been enhanced after term-term relation analysis which results in improved similarity estimation of relevant items with the user profiles.The experimentation result proves that the proposed methodology improves the overall search and retrieval results as compared to the state-of-art algorithms.

Highlights

In present scenario, information is continuously being generated with a velocity which is much higher than our processing capacity
The underestimated features of user profiles have been enhanced after term-term relation analysis, which results in improved similarity estimation of relevant items with the user profiles
The proposed methodology for incorporating the user-profiles with semantic intelligence based on term-term coupling learning is given by the block diagram as shown in figure 1. The steps involved such as user profile construction, item representation, term-term relation analysis and user feature enhancement have been explained in detail

Summary

Introduction

Information is continuously being generated with a velocity which is much higher than our processing capacity. The recommendation techniques that exist can be broadly categorized into content-based techniques (Lops et al, 2011), collaborative filtering techniques (Linden et al, 2003), hybrid techniques (Balabanovic & Shoham, 1997) and personalized techniques. In user-user collaborative filtering, the like-minded users or the users having the same interests are identified by the kind of ratings they give to the items or by what items they purchase, view or like. The recommendations on e-commerce sites such as Amazon are based on item-item collaborative filtering where products that are mostly purchased along with the products of user interest are recommended to the user. Many hybrid techniques which are a fusion of other recommendation techniques exist and non-personalized techniques such as recommending the top-rated products irrespective of what inclination the user has are in practice

Methods

Results

Conclusion