Vohra A, Garg R. Deep learning based sentiment analysis of public perception of working from home through tweets.
J Intell Inf Syst 2023;
60:255-274. [PMID:
36034686 PMCID:
PMC9399597 DOI:
10.1007/s10844-022-00736-2]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2022] [Revised: 08/01/2022] [Accepted: 08/08/2022] [Indexed: 11/26/2022]
Abstract
Nowadays, we are witnessing a paradigm shift from the conventional approach of working from office spaces to the emerging culture of working virtually from home. Even during the COVID-19 pandemic, many organisations were forced to allow employees to work from their homes, which led to worldwide discussions of this trend on Twitter. The analysis of this data has immense potential to change the way we work but extracting useful information from this valuable data is a challenge. Hence in this study, the microblogging website Twitter is used to gather more than 450,000 English language tweets from 22nd January 2022 to 12th March 2022, consisting of keywords related to working from home. A state-of-the-art pre-processing technique is used to convert all emojis into text, remove duplicate tweets, retweets, username tags, URLs, hashtags etc. and then the text is converted to lowercase. Thus, the number of tweets is reduced to 358,823. In this paper, we propose a fine-tuned Convolutional Neural Network (CNN) model to analyse Twitter data. The input to our deep learning model is an annotated set of tweets that are effectively labelled into three sentiment classes, viz. positive negative and neutral using VADER (Valence Aware Dictionary for sEntiment Reasoning). We also use a variation in the input vector to the embedding layer, by using FastText embeddings with our model to train supervised word representations for our text corpus of more than 450,000 tweets. The proposed model uses multiple convolution and max pooling layers, dropout operation, and dense layers with ReLU and sigmoid activations to achieve remarkable results on our dataset. Further, the performance of our model is compared with some standard classifiers like Support Vector Machine (SVM), Naive Bayes, Decision Tree, and Random Forest. From the results, it is observed that on the given dataset, the proposed CNN with FastText word embeddings outperforms other classifiers with an accuracy of 0.925969. As a result of this classification, 54.41% of the tweets are found to show affirmation, 24.50% show a negative disposition, and 21.09% have neutral sentiments towards working from home.
Collapse