Opinion Mining and Tweet Analysis Using Topic Modeling by LDA with BERT and GLOVE Embedding

DOI

10.2991/978-94-6463-196-8_50How to use a DOI?

Keywords

Opinion Mining; Glove Model; BERT Model; LSTM Model; Principal Component Analysis; K-means

Abstract

An example of natural language processing is opinion mining. A system is created to gather and process opinions about a product expressed in blog posts, comments, reviews, or tweets in order to assess public sentiment. Data preprocessing is used in this study to clean tweets and remove any punctuation, special symbols, hashtags, and URLs. Topic modelling and LDA are used to extract the themes from the corpus of gathered topics. The Principal Components Analysis (PCA) techniques are described in this article as dimensional reduction strategies with the goal of identifying the fewest possible Principal Components (PCs) that can help achieve the best classification performance. K-means clustering is a technique used to group together comparable words in tweets, along with cluster analysis. Utilizing the glove model, words are represented as vectors. The tweets can be grouped using k-means. Text input is sequentially read using the BERT paradigm. LSTM (long short-term memory) is used to anticipate sequences. In order to maintain the semantic association between words in a low-dimensional embedding space, Word2vec is a potent and effective word embedding technique. It is capable of handling tiny text corpora with a few million unique words (also called as vocabulary). “T- SNE” that places each datapoint on a two- or three-dimensional map to view high-dimensional data. In order to more effectively validate models and outcomes, other performance metrics like accuracy, F1-score, and a confusion matrix were also used.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ashwini Pachlore
AU  - Vrishali Chakkarwar
PY  - 2023
DA  - 2023/08/10
TI  - Opinion Mining and Tweet Analysis Using Topic Modeling by LDA with BERT and GLOVE Embedding
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 660
EP  - 673
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_50
DO  - 10.2991/978-94-6463-196-8_50
ID  - Pachlore2023
ER  -