Twitter Sentiment Classification Research Articles

Fine-Grained Sentiment Classification Using Generative Pretrained Transformer

Social media platforms have seen a significant increase in the number of users and content in recent years. Owing to the increased usage of these platforms, incidents of teasing, provocation—both positive and negative—and harassment, and community attacks have increased tremendously. There is an urgent need to automatically identify such content or tweets that can hamper the well-being of an individual or society. Analyzing social media messages from Twitter and Facebook has become the focus of sentiment analysis in recent years, which formerly focused on online product evaluations. Sentiment analysis is used in a wide range of fields besides product reviews, including harassment, stock markets, elections, disasters, and software engineering. After the tweets have been preprocessed, the extracted features are categorized using classifiers like decision trees, logistic regression, multinomial nave Bayes, support vector machines, random forests, and Bernoulli nave Bayes, as well as deep learning techniques like recurrent neural network (RNN) models, long short-term memory (LSTM) models, bidirectional long short-term memory (BiLSTM) models, and convolutional neural network (CNN) model for sentiment analysis. In this paper, different techniques are compared to classify Twitter tweets into three categories: “positive,” “negative,” and “neutral.” We proposed a novel data-balancing technique for text classification. A text classification technique is proposed for analyzing textual data using the Generative Pretrained Transformer model owing to its contextual understanding and more realistic data generation capability. Comparative analysis of different Machine learning and Deep learning models are performed with and without data balancing. The experiments show that the accuracy and F1-measure of the Twitter sentiment classification classifier are improved. The proposed ensemble has outperformed and achieved an accuracy of 90%, precision of 88%, and 81% F1 score.

A novel ensemble approach for Twitter sentiment classification with ML and LSTM algorithms for real-time tweets analysis

Social media sentiment classification was an essential consideration in natural language processing (NLP) for evaluating normal people’s perspectives on a given topic. With Twitter’s massive rise in popularity in recent years, the capacity to extract information about public sentiment from tweets became a major focus. This paper not only analyzed public sentiment through data from Twitter but introduced a novel ensemble approach in the methods employed for Twitter sentiment classification. Real-time tweets on various topics, including “covid,” “crime,” “spam,” “flipkart,” “migraine,” and “airlines,” were extracted and thoroughly examined to gain insight into public opinions. Leveraging the Twitter API for real-time tweet extraction, natural language processing techniques were applied to clean the tweet data. Subsequently, we applied several machine learning (ML) algorithms Naïve Bayes, decision tree (DT), random forest (RF), logistic regression (LGR), and deep learning (DL) algorithms recurrent neural network (RNN), LSTM, and GRU individually. Later, we proposed a novel ensemble of ML and DL algorithms for sentiment classification, with a novel emphasis on ensemble techniques and enhanced the accuracy with a significance compared to individual ML or DL model applied. The experimental results demonstrated that our novel ensemble approach achieved high accuracy when compared to existing work.

Evaluation of adjective and adverb types for effective Twitter sentiment classification.

Twitter, the largest microblogging platform, has reported more than 330 million active users in recent years. Many users express their sentiments about politics, sports, products, personalities, etc. Sentiment analysis has emerged as a specialized branch of machine learning in which tweets are binary-classified to provide sentimental insights. A major step in sentiment classification is feature selection, which primarily revolves around parts of speech (POS). Few techniques merely focused on single features such as adjectives, adverbs, and verbs, while other techniques examined types of these features, such as comparative adjectives, superlative adjectives, or general adverbs. Furthermore, POS as linguistic entities have also been studied and extensively classified by researchers, such as CLAWS-C7. For sentiment analysis, none of the studies conceptualized all possible POS features under similar conditions to draw firm conclusion. This research is centered on the following objectives: 1) examining the impact of various types of adjectives and adverbs that have not been previously explored for sentiment classification; 2) analyzing potential combinations of adjectives and adverbs types 3) conducting a comparison with a benchmark dataset for better classification accuracy. To assess the concept, a renowned human annotated dataset of tweets is investigated. Results showed that classification accuracy for adjectives is improved up to 83% based on the general superlative adjective whereas for adverbs, comparative general adverb also depicted significant accuracy improvement. Their combination with general adjectives and general adverbs also played a substantial role. The unexplored potential of adjectives and adverb types proved better in accuracy against state-of-the-art probabilistic model. In comparison to lexicon-based model, proposed research model overruled the dependency of lexicon-based dictionary where each term first needs to be matched for semantic orientation. The evident outcomes also help in time reduction aspect where huge volume of data need to be processed swiftly. This noteworthy contribution brought up significant knowledge and direction for domain experts. In the future, the proposed technique will be explored for other types of textual data across different domains.

Leveraging distant supervision and deep learning for twitter sentiment and emotion classification

Nowadays, various applications across industries, healthcare, and security have begun adopting automatic sentiment analysis and emotion detection in short texts, such as posts from social media. Twitter stands out as one of the most popular online social media platforms due to its easy, unique, and advanced accessibility using the API. On the other hand, supervised learning is the most widely used paradigm for tasks involving sentiment polarity and fine-grained emotion detection in short and informal texts, such as Twitter posts. However, supervised learning models are data-hungry and heavily reliant on abundant labeled data, which remains a challenge. This study aims to address this challenge by creating a large-scale real-world dataset of 17.5 million tweets. A distant supervision approach relying on emojis available in tweets is applied to label tweets corresponding to Ekman’s six basic emotions. Additionally, we conducted a series of experiments using various conventional machine learning models and deep learning, including transformer-based models, on our dataset to establish baseline results. The experimental results and an extensive ablation analysis on the dataset showed that BiLSTM with FastText and an attention mechanism outperforms other models in both classification tasks, achieving an F1-score of 70.92% for sentiment classification and 54.85% for emotion detection.

Harnessing Twitter: Sentiment Analysis for Predicting Election Outcomes in India

This paper explores the potential of Twitter, a popular social media platform, as a tool for predicting election outcomes. Sentiment analysis has emerged as a powerful tool for predicting election outcomes, with numerous studies showcasing its effectiveness in various countries. For instance, research has utilized sentiment analysis to forecast election results in nations like the USA, India, Pakistan and other countries, demonstrating the utility of social media data in gauging public opinion and predicting electoral results [1]. Elections in India are always considered important events that most people look forward to the rapid growth of social media in the past has provided end users with powerful tools to share their ideas. Twitter, which is one such platform, provides daily updates on political events through various hashtags and trends. People react to political events and give their opinions. Our approach is to collect tweets from top political parties contesting the Gujarat Assembly Elections 2022, and then calculate sentiment scores. The database includes a variety of recent and well-liked tweets about a specific political party. Party tweets are generated with specific keywords like “BJP”, “AAP”,“Congress” and so on. In the context of India, Twitter sentiment analysis tools and classification have been used to predict the outcomes of state assembly elections, underscoring the potential of social media data in forecasting electoral results within the country [2]. We used standard machine learning algorithms like VADER sentiment analyzer on Random Forest and Decision Tree for our classification and testing data to classify tweets as positive and negative. As a result, this work uses sentiment analysis to evaluate tweets gathered from Twitter and forecast election outcomes. This work shows the growing influence of social media on politics and the feasibility of using such platforms for predictive analysis. The findings of this study could provide valuable insights for political parties, policymakers, and researchers interested in the intersection of social media and politics. Random Forest and Decision Tree models performed well in predicting election outcomes based on sentiment analysis on Twitter data with 89% and 86% respectively.

Low-Resource Language Information Processing using Dwarf Mongoose Optimization with Deep Learning Based Sentiment Classification

Asian and low-resource language information processing refers to the field of computational linguistics that aims to develop natural language processing (NLP) technologies for languages that have fewer available language resources or are less commonly spoken. This is an important field of study because many languages in Asia and other parts of the world are underrepresented in the field of NLP, which may limit access to information and technology for speakers of these languages. The growing volume of user-generated content on the web has made sentiment analysis (SA) a significant tool for extracting data regarding human emotional states. Twitter sentiment detectors provide a superior solution for assessing the quality of products and services compared to other conventional technologies. The detection performance and classifier accuracy of SA, which can be highly dependent on classifier methods and the quality of input features have been utilised. Deep learning (DL) methods use distinct techniques to extract data from raw data such as tweets or texts and represent them in different forms of models. Therefore, this article presents a Dwarf Mongoose Optimization with Deep Learning-Based Twitter Sentiment Classification (DMODL-TSC) technique to classify sentiments based on tweets. The presented DMODL-TSC technique leverages the concepts of natural language processing (NLP) and DL. Primarily, the raw tweets are preprocessed to transform them into a useful format. Next, the DMODL-TSC technique uses the advanced FastText word embedding technique. Moreover, the bidirectional recurrent neural network (BiRNN) method is utilized for the recognition of sentiments. Finally, the DMO technique is utilized for the optimal hyperparameter optimization of the BiRNN method, which leads to effective classification performance. The comprehensive result examination of the DMODL-TSC system was tested on three datasets, and the obtained outcomes illustrate the supremacy of the DMODL-TSC approach.

Sentiment Analyzing from Tweet Data’s Using Bag of Words and Word2Vec

Twitter sentiment classification is an artificial approach for examining textual information and figuring out what people's publicly tweets from a variety of industries are experiencing or thinking. For instance, a large number of tweets containing hashtags are posted online every minute from one user to some other user in the commercial and politics fields. It can be challenging for scientists to correctly comprehend the context in which specific tweet terms are used, necessitating a challenge in determining what is actually a positive or negative comment from the vast database of twitter data. The system's authenticity is violated by this issue and user dependability may be significantly diminished. In this study, twitter data sent to interpret movies were classified using various classifier and feature methods. In this context, the IMDB database consisting of 50000 movie reviews was used. For the purpose of anticipating the sentimental tweets for categorization, a huge proportion of twitter data is analyzed. In the proposed method, bag of words and word2vec methods are given by combining them instead of giving them separately to the classifier. With both the suggested technique, the system's effectiveness is increased and the data that are empirically obtained from the real world situation may be distinguished well. With experimental efficiency of 90%, the suggested approach algorithms' output attempts to assess the reviews tweets as well as be able to recognize movie reviews.

Dual-Track Lifelong Machine Learning-Based Fine-Grained Product Quality Analysis

Artificial intelligence (AI) systems are becoming wiser, even surpassing human performances in some fields, such as image classification, chess, and Go. However, most high-performance AI systems, such as deep learning models, are black boxes (i.e., only system inputs and outputs are visible, but the internal mechanisms are unknown) and, thus, are notably challenging to understand. Thereby a system with better explainability is needed to help humans understand AI. This paper proposes a dual-track AI approach that uses reinforcement learning to supplement fine-grained deep learning-based sentiment classification. Through lifelong machine learning, the dual-track approach can gradually become wiser and realize high performance (while keeping outstanding explainability). The extensive experimental results show that the proposed dual-track approach can provide reasonable fine-grained sentiment analyses to product reviews and remarkably achieve a 133% promotion of the Macro-F1 score on the Twitter sentiment classification task and a 27.12% promotion of the Macro-F1 score on an Amazon iPhone 11 sentiment classification task, respectively.

ANALISIS SENTIMEN TWITTER TERHADAP WACANA PENUNDAAN PEMILU DENGAN METODE SUPPORT VECTOR MACHINE

Machine learning plays an important role in managing important issues to classify and predict information that develops ahead of the General Election in Indonesia. Especially in knowing public sentiment on the discourse on the postponement of the 2024 election through Twitter social media. So it is necessary to analyze the discourse by categorizing it as positive or negative. The Support Vector Machine (SVM) model is used for analysis and classification. The sample data used were 100 tweets data which were then scraped in the period January 2022 – May 2022. The processing was done using Python programming and Jupyter Lab tools. Before doing the analysis, do preprocess to eliminate unnecessary words and information so that the level of accuracy of the results of this Twitter sentiment classification can provide a closer picture of reality. As for the results of the grouping carried out positive sentiment in as many as 40 data tweets and negative sentiment in as many as 60 data tweets. The classification test results on tweets data with a good level of accuracy of 92%. These results are expected to be a reference for future researchers who want to improve accuracy or analysis results.

Comparative Analysis and Design of Different Approaches for Twitter Sentiment Analysis and classification using SVM

Companies and organizations have always found that the views and feedback of the community are their most important and valuable resource. With everyone using social media more and more, it makes it possible to analyze and evaluate things in ways that have never been done before. Before, organizations had to use methods that were unusual, time-consuming, and prone to mistakes. This way of analyzing fits right into the field of "sentiment analysis." Sentiment analysis is a broad field that deals with putting user-generated text into well-defined groups. There are a number of tools and algorithms that can be used to detect and analyze sentiment. For example, supervised machine learning algorithms can be trained with training data and then used to classify the target corpus. Lexical techniques, which use a dictionary-based annotated corpus to do classification, and hybrid tools, which are a mix of machine learning and lexicon-based algorithms, are also used. In this paper, we used Weka's Support Vector Machine (SVM) to analyze how people feel about something. SVM is a popular supervised machine learning algorithm used to find the polarity of text. The main objective is to analyze the emotions expressed in tweets using various simulations of artificial intelligence that classify tweets as positive or negative. If a tweet has both positive and negative components, the more prevalent component should be chosen as the closing statement. Emojis, usernames, and hashtags in tweets should be controlled and transformed into a standard development. Sincerely, these events' planners have started looking into these inconspicuous web blogs (online diaries) to acquire a feel for their niche. On other discreet sites, they routinely monitor and respond to customer feedback. Better means of seeing and combining a broad assessment are one challenge. A few people, including Facebook, Twitter, and Instagram, were really introduced to social affiliation stages a year ago. The vast majority of individuals utilize internet entertainment to express their thoughts about objects, places, or people. Systems Twitter, a less common platform for publishing material to blogs, is a huge repository of well-known reviews for various persons, services, associations, and products, among other things. Assessment examinations are reviews of the public assessment structures. What is said on Twitter has a substantial context thanks to a mixture of opinions. The widespread accessibility of online tests and virtual entertainment posts in the media provides connection with crucial examination to undermine expert judgments and direct their boosting strategies to relaxing and client conclusions. In this way, virtual distraction anticipates playing a significant role in influencing the general exposure of the companies or objects selected. This study highlights the many approaches used for item depiction analyses. Check topics on Twitter to see if the general public is acting in a favorable, negative, or neutral manner.

A sentiment analysis of the Black Lives Matter movement using Twitter

As more attention is brought to the issue of racial injustice, public sentiments and opinions on racial issues are increasingly important to track. At the same time, recent progress in machine learning and natural language processing methods, coupled with the growing amount of available data for training and analysis, allows researchers to extract sentiments from text data at large scales. We applied a natural language processing framework to study public sentiment surrounding the Black Lives Matter (BLM) movement. Specifically, we used a state-of-the-art BERT model fine-tuned for Twitter sentiment classification to predict the sentiment from approximately 1 million tweets from July 2013 to March 2021 related to BLM. The BERT model was trained on the Sentiment 140 dataset on which it obtained an AUC of 0.97 on the training data and 0.94 on testing data, outperforming other machine learning models. We found that retweet frequency and word count frequency were able to illustrate important themes in the BLM movement as well as indicate events of significant importance to the movement. Additionally, sentiment analysis revealed which of these themes and events were associated with positive public sentiment, such as social justice, and which were associated with negative sentiment, such as police brutality. Our analyses can also be applied to better understand other social and political movements to aid related research and activism.

Competitive Capsule Network Based Sentiment Analysis on Twitter COVID’19 Vaccines

COVID-19 is an extremely contagious virus that has rapidly spread around the world. This disease has infected people of all ages in India, from children to the elderly. Vaccination, on the other hand, is the only way to preserve human lives. In the midst of a pandemic, it’s critical to know what people think of COVID-19 immunizations. The primary goal of this article is to examine corona vaccination tweets from India’s Twitter social media. This study introduces CompCapNets, a unique deep learning approach for Twitter sentiment classification. The results suggest that the proposed method outperforms other strategies when compared to existing traditional methods.

A unified deep neuro-fuzzy approach for COVID-19 twitter sentiment classification

Covid-19 braces serious mental health crisis across the world. Since a vast majority of the population exploit social media platforms such as twitter to exchange information, rapid collecting and analyzing social media data to understand personal well-being and subsequently adopting adequate measures could avoid severe socio-economic damage. Sentiment analysis on twitter data is very useful to understand and identify the mental health issues. In this research, we proposed a unified deep neuro-fuzzy approach for Covid-19 twitter sentiment classification. Fuzzy logic has been a very powerful tool for twitter data analysis where approximate semantic and syntactic analysis is more relevant because correcting spelling and grammar in tweets are merely obnoxious. We conducted the experiment on three challenging COVID-19 twitter sentiment datasets. Experimental results demonstrate that fuzzy Sugeno integral based ensembled classifiers succeed over individual base classifiers.

Deep Learning and TextBlob Based Sentiment Analysis for Coronavirus (COVID-19) Using Twitter Data

The novel Coronavirus (COVID-19) has affected the normal life of people around the world and has forced them to maintain social distance, self-quarantine and closing of many businesses. So, the people wish to share the information regarding the pandemic through social media e.g. Twitter. The key objective of this paper is to identify the sentiment associated with the pandemic by utilizing the tweets regarding the Coronavirus (COVID-19) and by using the python libraries to perform the task. We analyze the sentiment of people when Coronavirus has attained a peak level using the machine, deep learning techniques and TextBlob. We have classified the sentiments into positive and negative classes using the Machine Learning (NB, SVM, Logistic regression) approaches and deep learning-based Bi-LSTM model. The Bi-LSTM approach has achieved better accuracy (0.87) compared to the traditional machine learning models for Twitter sentiment classification. From the overall analysis, we could conclude that people are confident and they express more positivity towards the recovery from the COVID-19 pandemic. Such an analysis will help the policy and decision-makers to address the needs of the public appropriately.

A ConvBiLSTM Deep Learning Model-Based Approach for Twitter Sentiment Classification

Being one of the most widely used social media tools, Twitter is seen as an important source of information for acquiring people's attitudes, emotions, views and feedbacks. Within this context, Twitter sentiment analysis techniques were developed to decide whether textual tweets express a positive or negative opinion. In contrast to lower classification performance of traditional algorithms, deep learning models, including Convolution Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM), have achieved a significant result in sentiment analysis. Although CNN can extract high-level local features efficiently by using convolutional layer and max-pooling layer, it cannot effectively learn sequence of correlations. On the other hand, Bi-LSTM uses two LSTM directions to improve the contexts available to deep learning algorithms, but Bi-LSTM cannot extract local features in a parallel way. Therefore, applying a single CNN or single Bi-LSTM for sentiment analysis cannot achieve the optimal classification result. An integrating structure of CNN and Bi-LSTM model is proposed in this study. ConvBiLSTM is implemented; a word embedding model which converts tweets into numerical values, CNN layer receives feature embedding as input and produces smaller dimension of features, and the Bi-LSTM model takes the input from the CNN layer and produces classification result. Word2Vec and GloVe were distinctly applied to observe the impact of the word embedding result on the proposed model. ConvBiLSTM was applied with retrieved Tweets and SST-2 datasets. ConvBiLSTM model with Word2Vec on retrieved Tweets dataset outperformed the other models with 91.13% accuracy.

SentiDiff: Combining Textual Information and Sentiment Diffusion Patterns for Twitter Sentiment Analysis

Twitter sentiment analysis has become a hot research topic in recent years. Most of existing solutions to Twitter sentiment analysis basically only consider textual information of Twitter messages, and struggle to perform well when facing short and ambiguous Twitter messages. Recent studies show that sentiment diffusion patterns on Twitter have close relationships with sentiment polarities of Twitter messages. Therefore, in this paper, we focus on how to fuse textual information of Twitter messages and sentiment diffusion patterns to obtain better performance of sentiment analysis on Twitter data. To this end, we first analyze sentiment diffusion by investigating a phenomenon called sentiment reversal , and find some interesting properties of sentiment reversals. Then, we consider the inter-relationships between textual information of Twitter messages and sentiment diffusion patterns, and propose an iterative algorithm called SentiDiff to predict sentiment polarities expressed in Twitter messages. To the best of our knowledge, this work is the first to utilize sentiment diffusion patterns to help improve Twitter sentiment analysis. Extensive experiments on real-world dataset demonstrate that compared with state-of-the-art textual information based sentiment analysis algorithms, our proposed algorithm yields PR-AUC improvements between 5.09 and 8.38 percent on Twitter sentiment classification tasks.

Sentiment Analysis by Fusing Text and Location Features of Geo-Tagged Tweets

Twitter sentiment analysis provides valuable feedback from public emotion concerning certain events or products. Current research has been focused on obtaining sentiment features from vectorized lexical and syntactic feature from tweets, without further context. In this paper, we demonstrated how vectorized location information could be combined with word embeddings to produce a hybrid representation, which has resulted in an improvement on a tweet sentiment classification task. The location information of the geo-tagged tweets provided further context, which was useful for a sentiment classification task. The tweets investigated contained a set of geo-tagged tweets. The word embeddings of these tweets were combined with the geo-tagged tweets' vectorized location features to form a sentiment feature set of geo-tagged tweets. The sentiment feature set was incorporated into a convolution neural network and a bi-directional long short-term memory network for the tasks of training and predicting of sentiment classification labels. This hybrid representation is compared with the baseline GloVe model through a few experiments, and the results have shown that the incorporation of vectorized location information has resulted in improvement of the accuracy for the twitter sentiment classification task.

Learning class-specific word embeddings

Recent years have seen the success of applying word embedding algorithms to natural language processing (NLP) tasks. Most word embedding algorithms only produce a single embedding per word. This makes the learned embeddings indiscriminative since many words are polysemous. Some prior work utilizes the context in which the word resides to learn multiple word embeddings. However, context-based solutions are problematic for short texts, such as tweets, which have limited context. Moreover, existing approaches tend to enumerate all possible context types of a particular word regardless of their target applications. Applying multiple vector representations per word in NLP tasks can be computationally expensive because all possible combinations of senses of words in a snippet need to be considered. Sometimes, a word sense can be captured when the class information or label of the short text is presented. For example, in a disaster-related dataset, when a text snippet is labeled as “hurricane related”, the word “water” in the snippet is more likely to be interpreted as rain and flood; when a snippet is labeled as “hurricane unrelated”, the word “water” can be interpreted as its more general meaning. In this work, we propose to use class information to enhance the discriminativeness of words. Instead of enumerating all potential senses per word in the text, the number of vector representations per word should be a function of the future classification task. We show that learning the number of vector representations per word according to the number of classes in the classification task is often sufficient to clarify the polysemy. Word embeddings learned from neural language models typically have the property of good linear compositionality. We utilize this property to encode class information into the vector representation of a word. We explore four approaches to train class-specific embeddings to encode class information by utilizing the label information and the linear compositionality property of word embeddings. We present a general framework consisting of a pair of convolutional neural networks to utilize the learned class-specific word embeddings as input for text classification tasks. We evaluate our approach and framework on topic classification of a disaster-focused Twitter dataset and a benchmark Twitter sentiment classification dataset from SemEval 2013. Our results show a relative accuracy improvement of 3–4% over a recent baseline.

Surface and Deep Features Ensemble for Sentiment Analysis of Arabic Tweets

Sentiment analysis (SA) of Arabic tweets is a complex task due to the rich morphology of the Arabic language and the informal nature of language on Twitter. Previous research on the SA of tweets mainly focused on manually extracting features from the text. Recently, neural word embeddings have been utilized as less labor-intensive representations than manual feature engineering. Most of these word-embeddings model the syntactic information of words while ignoring the sentiment context. In this paper, we propose to learn sentiment-specific word embeddings from Arabic tweets and use them in the Arabic Twitter sentiment classification. Moreover, we propose a feature ensemble model of surface and deep features. The surface features are manually extracted features, and the deep features are generic word embeddings and sentiment-specific word embeddings. The extensive experiments are performed to test the effectiveness of the surface and deep features ensemble, pooling functions, embeddings size, and cross-dataset models. The recent language representation model BERT is also evaluated on the task of SA of Arabic tweets. The models are evaluated on three different datasets of Arabic tweets, and they outperform the previous results on all these datasets with a significant increase in the F-score. The experimental results demonstrate that: 1) the highest performing model is the ensemble of surface and deep features and 2) the approach achieves the state-of-the-art results on several benchmarking datasets.

Multi-class Twitter sentiment classification with emojis

PurposeRecently, various Twitter Sentiment Analysis (TSA) techniques have been developed, but little has paid attention to the microblogging feature – emojis, and few works have been conducted on the multi-class sentiment analysis of tweets. The purpose of this paper is to consider the popularity of emojis on Twitter and investigate the feasibility of an emoji training heuristic for multi-class sentiment classification of tweets. Tweets from the “2016 Orlando nightclub shooting” were used as a source of study. Besides, this study also aims to demonstrate how mapping can contribute to interpreting sentiments.Design/methodology/approachThe authors presented a methodological framework to collect, pre-process, analyse and map public Twitter postings related to the shooting. The authors designed and implemented an emoji training heuristic, which automatically prepares the training data set, a feature needed in Big Data research. The authors improved upon the previous framework by advancing the pre-processing techniques, enhancing feature engineering and optimising the classification models. The authors constructed the sentiment model with a logistic regression classifier and selected features. Finally, the authors presented how to visualise citizen sentiments on maps dynamically using Mapbox.FindingsThe sentiment model constructed with the automatically annotated training sets using an emoji approach and selected features performs well in classifying tweets into five different sentiment classes, with a macro-averaged F-measure of 0.635, a macro-averaged accuracy of 0.689 and the MAEM of 0.530. Compared to those experimental results in related works, the results are satisfactory, indicating the model is effective and the proposed emoji training heuristic is useful and feasible in multi-class TSA. The maps authors created, provide a much easier-to-understand visual representation of the data, and make it more efficient to monitor citizen sentiments and distributions.Originality/valueThis work appears to be the first to conduct multi-class sentiment classification on Twitter with automatic annotation of training sets using emojis. Little attention has been paid to applying TSA to monitor the public’s attitudes towards terror attacks and country’s gun policies, the authors consider this work to be a pioneering work. Besides, the authors have introduced a new data set of 2016 Orlando Shooting tweets, which will be made available for other researchers to mine the public’s political opinions about gun policies.