Application of Latent Dirichlet Allocation (LDA) for clustering financial tweets

Sifi Fatima-Zahrae,Sabbar Wafae,El Mzabi Amal,S Krit

doi:10.1051/e3sconf/202129701071

Abstract

Sentiment classification is one of the hottest research areas among the Natural Language Processing (NLP) topics. While it aims to detect sentiment polarity and classification of the given opinion, requires a large number of aspect extractions. However, extracting aspect takes human effort and long time. To reduce this, Latent Dirichlet Allocation (LDA) method have come out recently to deal with this issue.In this paper, an efficient preprocessing method for sentiment classification is presented and will be used for analyzing user’s comments on Twitter social network. For this purpose, different text preprocessing techniques have been used on the dataset to achieve an acceptable standard text. Latent Dirichlet Allocation has been applied on the obtained data after this fast and accurate preprocessing phase. The implementation of different sentiment analysis methods and the results of these implementations have been compared and evaluated. The experimental results show that the combined uses of the preprocessing method of this paper and Latent Dirichlet Allocation have an acceptable results compared to other basic methods.

Highlights

With the emergence and rapid development of Web 2.0, moreand more people begin to express their feelings, opinion andattitude over Internet, which increase the amount of usergeneratedreviews containing rich opinion and sentimentinformation
We have described Latent Dirichlet Allocation (LDA), a topic modeling based method for aspect clustering for collection of data
LDA is based on a simple exchangeability assumption for the words and topics in a document

Summary

Introduction

With the emergence and rapid development of Web 2.0, moreand more people begin to express their feelings, opinion andattitude over Internet, which increase the amount of usergeneratedreviews containing rich opinion and sentimentinformation. One big problem is to find aspects that users evaluate in reviews. From the perspective of a user reading the reviews to get information about a product, the evaluations of the specific aspects are just as important as the overall rating of the product. Sometimes the aspect information is available, it isunlikely to be a comprehensive set of all aspects that areevaluated in the reviews Another important task in reviewanalysis is discovering how opinions and sentiments for different aspects are expressed. „The company is in financial difficulties‟, and „She organizes her financial affairs very efficiently‟. These are sentiment words at the level of theaspect.

Related Work

Latent Dirichlet Allocation

LDA implementation for clustering financial tweets

Dataset

Experimental results

Conclusion