Food Interests Analysis (FIA) model to extract the food preferences and interests of Twitter users

Document Type : Original full papers (regular papers)

Authors

1 Information Systems, Faculty of Computers and Artificial Intelligence, Fayoum University, Fayoum, Egypt

2 Department of Computer Science, Community College, Imam AbdulRahman Bin Faisal University, Dammam 31441, Saudi Arabia

3 Department of Information Systems, Faculty of Computers and Artificial Intelligence, Fayoum University, El Fayoum 63514, Egypt

Abstract

Online social networks like Facebook and Twitter have played an important role in networking, disseminating information, and sharing interests and entertainment since the internet's advent into our daily lives. Twitter has significantly contributed to the analysis of its user-generated data for personalization and tasks of recommendation due to its rapid growth as a social networking platform. Twitter posts serve as an important source of information for identifying users' positive interests and creating intelligent recommendation systems. These posts provide a lot of information that may be analyzed to determine users' preferences on various topics, including food. Twitter post analysis is an interesting field of study. Several studies have studied the sentiment analysis of tweets. Also, market forecasting is a crucial issue that requires careful consideration. Business intelligence (BI) becomes an important analytical technique for assessing consumer satisfaction and market demand. Since business intelligence requires in-depth analysis, sentiment analysis is the process of using natural language processing (NLP) and machine learning (ML) techniques to identify the emotional tone and attitude in text, making it useful for analyzing Twitter posts and customer reviews and identifying user preferences and market demand. As a result, it's critical to choose relevant advertisements for users at particular locations to capture their attention and generate profit. This paper develops a proposed model for a Food Interests Analysis (FIA). It collects 20,000 publicly available tweets, and then the sentiments conveyed in the tweets are captured and normalized, then clustered according to the common topic. This paper also examines the accuracy of two lexicon-based sentiment analysis approaches for tweets. Also, this study proposes an approach that combines both topic modeling and sentiment analysis (SA) by Latent Dirichlet Allocation (LDA) using the term frequency-inverse document frequency (TF-IDF) and extracting sentiment from tweets. Thus, this approach can identify the food preference categories in which users are interested.  

Keywords

Main Subjects

Files

Share

How to cite

Statistics