With advanced digitalisation, we can observe a massive increase of user-generated content on the web that provides opinions of people on different subjects. Sentiment analysis is the computational study of analysing people's feelings and opinions for an entity. The field of sentiment analysis has been the topic of extensive research in the past decades. In this paper, we present the results of a tertiary study, which aims to investigate the current state of the research in this field by synthesizing the results of published secondary studies (i.e., systematic literature review and systematic mapping study) on sentiment analysis. This tertiary study follows the guidelines of systematic literature reviews (SLR) and covers only secondary studies. The outcome of this tertiary study provides a comprehensive overview of the key topics and the different approaches for a variety of tasks in sentiment analysis. Different features, algorithms, and datasets used in sentiment analysis models are mapped. Challenges and open problems are identified that can help to identify points that require research efforts in sentiment analysis. In addition to the tertiary study, we also identified recent 112 deep learning-based sentiment analysis papers and categorized them based on the applied deep learning algorithms. According to this analysis, LSTM and CNN algorithms are the most used deep learning algorithms for sentiment analysis.

/pdf/systematic-reviews-in-sentiment-analysis-a-tertiary-study-40dbx65681.pdf

Systematic reviews in sentiment analysis: a tertiary study

A vast amount of data is generated every second for microblogs, content sharing via social media sites, and social networking. Twitter is an essential popular microblog where people voice their opinions about daily issues. Recently, analyzing these opinions is the primary concern of Sentiment analysis or opinion mining. Efficiently capturing, gathering, and analyzing sentiments have been challenging for researchers. To deal with these challenges, in this research work, we propose a highly accurate approach for SA of fake news on COVID-19. The fake news dataset contains fake news on COVID-19; we started by data preprocessing (replace the missing value, noise removal, tokenization, and stemming). We applied a semantic model with term frequency and inverse document frequency weighting for data representation. In the measuring and evaluation step, we applied eight machine-learning algorithms such as Naive Bayesian, Adaboost, K-nearest neighbors, random forest, logistic regression, decision tree, neural networks, and support vector machine and four deep learning CNN, LSTM, RNN, and GRU. Afterward, based on the results, we boiled a highly efficient prediction model with python, and we trained and evaluated the classification model according to the performance measures (confusion matrix, classification rate, true positives rate...), then tested the model on a set of unclassified fake news on COVID-19, to predict the sentiment class of each fake news on COVID-19. Obtained results demonstrate a high accuracy compared to the other models. Finally, a set of recommendations is provided with future directions for this research to help researchers select an efficient sentiment analysis model on Twitter data.

/pdf/detection-of-fake-news-text-classification-on-covid-19-using-4mq20lm92n.pdf

Detection of Fake News Text Classification on COVID-19 Using Deep Learning Approaches.

An emotional classification method of Chinese short comment text based on ELECTRA

Transformer-based deep learning models for the sentiment analysis of social media data

Emojis are being frequently used in today’s digital world to express from simple to complex thoughts more than ever before. Hence, they are also being used in sentiment analysis and targeted marketing campaigns. In this work, we performed sentiment analysis of Tweets as well as on emoji dataset from the Kaggle. Since tweets are sentences we have used Universal Sentence Encoder (USE) and Sentence Bidirectional Encoder Representations from Transformers (SBERT) end-to-end sentence embedding models to generate the embeddings which are used to train the Standard fully connected Neural Networks (NN), and LSTM NN models. We observe the text classification accuracy was almost the same for both the models around 98%. On the contrary, when the validation set was built using emojis that were not present in the training set then the accuracy of both the models reduced drastically to 70%. In addition, the models were also trained using the distributed training approach instead of a traditional singlethreaded model for better scalability. Using the distributed training approach, we were able to reduce the run-time by roughly 15% without compromising on accuracy. Finally, as part of explainable AI the Shap algorithm was used to explain the model behaviour and check for model biases for the given feature set.

Syeda Maliha Marium

Papers

An algorithm and method for sentiment analysis using the text and emoticon