SENTIMENT ANALYSIS OF WEB 3.0 ENABLED TWITTER DATASET

The sentiment analysis process that gives this work its name is the main theme of the work. Since the beginning of 2000, sentiment analysis has become one of the most active research areas by researchers working on natural language processing and social networking analysis. In addition, data mining, web mining, and text mining are also studied extensively. Moreover, the method of sentiment analysis has spread over many fields, from computer science to management science, from social science to economics, due to the importance given to the business world as a whole and the collectivity. In this study, Konstanz Information Miner (KNIME), which is a powerful data mining tool with its richest features and many visualization tools, was used on twitter data. Ten thousand Twitter data were used in this study. The sentiment analysis study, which is in fact a classification study, was conducted using machine learning algorithms on Twitter data. The results of the study were interpreted by carrying out an accuracy analysis. It is anticipated that the use of the KNIME, which has rich visualization tools, will be widespread in sentiment analysis studies to make these works both easier and more reliable.

A hybrid machine learning model for sentiment analysis and satisfaction assessment with Turkish universities using Twitter data

The explosive increase in Internet usage has attracted technologies for automatically mining the user-generated contents (UGC) from Web documents. These UGC-rich resources have raised new opportunities and challenges to carry out the opinion extraction and mining tasks for opinion summaries. The technology of opinion extraction allows users to retrieve and analyze people’s opinions scattered over Web documents. Opinion mining is a process which is concerned with the opinions generated by the consumers about the product. Opinion Mining aims at understanding, extraction and classification of opinions scattered in unstructured text of online resources. The search engines performs well when one wants to know about any product before purchase, but the filtering and analysis of search results often complex and time-consuming. This generated the need of intelligent technologies which could process these unstructured online text documents through automatic classification, concept recognition, text summarization, etc. These tools are based on traditional natural language techniques, statistical analysis, and machine learning techniques. Automatic knowledge extraction over large text collections like Internet has been a challenging task due to many constraints such as needs of large annotated training data, requirement of extensive manual processing of data, and huge amount of domain-specific terms. Ambient Intelligence (AmI) in wed-enabled technologies supports and promotes the intelligent e-commerce services to enable the provision of personalized, self-configurable, and intuitive applications for facilitating UGC knowledge for buying confidence. In this chapter, we will discuss various approaches of Opinion Mining which combines Ambient Intelligence, Natural Language Processing and Machine Learning methods based on textual and grammatical clues.

Objective: To make an extensive analysis of sentiment within the discourse surrounding COVID-19 vaccines on Twitter, employing Natural Language Processing (NLP) methodologies. Method: The research methodology encompasses data collection via the Twitter API, followed by sentiment analysis facilitated by the TextBlob library. Pre-processing stages are integrated to cleanse and standardize the Twitter data. Subsequently, sentiment analysis categorizes tweets into positive, negative, and neutral sentiments based on polarity scores. Findings: The findings, grounded in a dataset spanning from March 1, 2022, to April 30, 2022, comprising 61,934 tweets, unveil that 45.0% of tweets conveyed positive sentiment, 17.3% exhibited negativity, and 37.7% maintained neutrality. Moreover, an exploration of tweet subjectivity revealed that 70.1% of the content expressed subjectivity, while 29.9% conveyed objectivity. The research is augmented with visual representations, including word clouds and subjectivity-polarity graphs, that offer a more intuitive understanding of sentiment trends. Novelty: This study contributes to the expanding landscape of sentiment analysis and its application within the context of public health crises, empowering stakeholders with valuable knowledge to enhance vaccine acceptance and effectiveness. The tool used “Tweet Downloader” in data collection makes this study different from other reviewed studies. Keywords: COVID-19 vaccine, Twitter sentiment analysis, Public perception, Natural Language Processing (NLP), Social media data

This thesis examines the issue of ill-formed text (microtext) and shows its impact on sentiment analysis. The source of microtext is Twitter, WhatsApp, Facebook and other social media platforms. Words or phrases not in their standard language format like “lol” (laugh out loud), “c u 2nite” (see you tonight) and “plz” (please) are called out of vocabulary (OOV) terms. On the other hand, words or phrases in their standard forms, for example, “tonight”, “love”, or “talk to you later”, are called In Vocabulary (IV) terms. The motivation behind microtext normalization is its growing presence on both online and offline platforms. Microtext might appear to be an ill-formed text, which requires find-and-replace methods. Traditionally, in a Natural Language Processing (NLP) context, microtexts such as abbreviations and length shortening or extending are normalized, but phonemic and graphemic variation is often ignored. However, the features of microtext can be traced back to social, cognitive and geographic influences. To understand social media text, it is essential to develop a microtext normalization module for traditional and modern NLP models. The first section of this thesis focuses on combining unsupervised learning methods in 2 different chapters, 4 and 5. The first method includes lexicon creation to transform the most frequent microtexts and emoticons on social media and applies them to sentiment analysis. This method shows an accuracy increase of 4% when microtext normalization is applied before sentiment analysis. This method is extended with an application to a pre-trained chatbot to improve the chatbot’s understanding of microtext (social media slangs). This method shows a mean BLEU score of 0.8 for the SMS and Tweet dataset. The second method incorporates a phonetic based approach to transform any microtext into its phonetic equivalent before 1normalizing it. This method shows an accuracy improvement of 6% for sentiment analysis on SenticNet. The second part of the unsupervised learning is in Chapter 5, introducing the IPA-based method for microtext normalization and sentiment analysis. Epitran was used to transform a word to its International Phonetic Alphabet (IPA) equivalent. The International Phonetic Alphabet (IPA) is an alphabetic system of phonetic notation based primarily on the Latin script. There is a significant improvement in microtext normalization task and sentiment analysis over Soundex. The results also show that there is very little redundancy when words are transformed to phonetics in IPA. In addition, the accuracy of polarity detection using this method has an improvement over baseline by 5%. Chapter 6 discusses a simple sequence-to-sequence based Deep Learning method. As the language is dynamic, it is not easy to maintain the lexicon. Deep Learning alleviates the static lexicon with a probabilistic model to transform microtext into its standard form. The findings suggest that a semiotic class of microtext was easy to transform, whereas the phonetic class of microtext was not handled easily. The proposed model improves the pre-trained sentiment analysis model by 4%. We also introduce a corpus for English microtext normalization. The corpus contains microtext-containing sentences along with their correctly spelt sentences and their correct polarity. This dataset can tackle two NLP problems, i.e., microtext normalization and sentiment analysis. This corpus consists of 38% positive, 39.9% negative and 22.1% neutral. A pre-trained model shows an accuracy of 46.4 % on OOV text for sentiment analysis, showing considerable room for improvement. In summary, this thesis introduces several approaches to microtext normalization analysis and focuses on sentiment analysis application. Microtext cannot be thought of as a one-dimensional problem to NLP. It encapsulates many factors like regional (geographical), ethnic (national and racial), and social (class, age, gender, socioeconomic status and education), which cannot be ignored given the growing importance of social media in our daily life.

According to data from the U.S. Center for Disease Control and Prevention, as of June 2020, a significant number of African Americans had been infected with the coronavirus disease, experiencing disproportionately higher death rates compared to other demographic groups. These disparities highlight the urgent need to examine the experiences, behaviors, and opinions of the African American population in relation to the COVID-19 pandemic. By understanding their unique challenges in navigating matters of health and well-being, we can work towards promoting health equity, eliminating disparities, and addressing persistent barriers to care. Since Twitter data has shown significant promise as a representation of human behavior and for opinion mining, this study leverages Twitter data published in 2020 to characterize the pandemic-related experiences of the United States’ African American population using aspect-based sentiment analysis. Sentiment analysis is a common task in natural language processing that identifies the emotional tone (i.e., positive, negative, or neutral) of a text sample. Aspect-based sentiment analysis increases the granularity of sentiment analysis by also extracting the aspect for which sentiment is expressed. We developed a machine learning pipeline consisting of image and language-based classification models to filter out tweets not related to COVID-19 and those unlikely published by African American Twitter subscribers, leading to an analysis of nearly 4 million tweets. Overall, our results show that the majority of tweets had a negative tone, and that the days with larger numbers of published tweets often coincided with major U.S. events related to the pandemic as suggested by major news headlines (e.g., vaccine rollout). We also show how word usage evolved throughout the year (e.g., outbreak to pandemic and coronavirus to covid). This work also points to important issues like food insecurity and vaccine hesitation, along with exposing semantic relationships between words, such as covid and exhausted. As such, this work furthers understanding of how the nationwide progression of the pandemic may have impacted the narratives of African American Twitter users.

Natural Language Processing (NLP) has emerged as a fundamental element of contemporary artificial intelligence, enabling systems that vary from chatbots to sentiment analyzers [1].Transforming unstructured text into organized, clean input is essential for attaining optimal performance in NLP tasks [2]. Regular expressions (RegEx) provide a rule-based, interpretable, and quick method for text tokenization, cleansing, and pattern extraction [3]. However, despite their effectiveness, RegEx methods are constrained by their failure to manage linguistic ambiguity and the variability present in natural language [4]. In comparison, machine learning (ML) models, particularly deep learning structures like BERT and LSTMs, offer strong semantic comprehension but necessitate vast amounts of training data and computational resources [5]. This document presents a hybrid framework that combines the rapid, rule based accuracy of RegEx with the profound semantic abilities of ML models to improve the overall performance of NLP systems [6]. We present a thorough literature review, elaborate algorithmdesigns complete with pseudocode, examples of code implementations, and an enhanced system architecture that remedies the limitations of existing methods [7]. The suggested method is assessed on benchmark tasks including sentiment analysis, named entity recognition (NER), and spam detection, demonstrating considerable advancements in both accuracy and efficiency [8].

Understanding the progress of the Sustainable Development Goals (SDGs) proposed by the United Nations (UN) is important, but difficult. In particular, policymakers would need to understand the sentiment within the public regarding challenges associated with climate change. With this in mind and the rise of social media, this work focuses on the task of uncovering the sentiment of Twitter users concerning climate-related issues. This is done by applying modern natural-language-processing (NLP) methods, i.e. VADER, TextBlob, and BERT, to estimate the sentiment of a gathered dataset based on climate-change keywords. A transfer-learning-based model applied to a pre-trained BERT model for embedding and tokenizing with logistic regression for sentiment classification outperformed the rule-based methods VADER and TextBlob; based on our analysis, the proposed approach led to the highest accuracy: 69%. The collected data contained significant noise, especially from the keyword ‘energy’. Consequently, using more specific keywords would improve the results. The use of other methods, like BERTweet, would also increase the accuracy of the model. The overall sentiment in the analyzed data was positive. The distribution of the positive, neutral, and negative sentiments was very similar in the different SDGs.

Sentiment analysis is a natural language processing approach that is widely implemented for many natural language processing applications such as translation, chatbots, and more. In this paper, news sentiment analysis in the stock market was reviewed. Stock market sentiment fluctuates because of events such as the reporting of quarterly financial report, macroeconomic data, government policy, etc. Traders use sentiment analysis to predict stock prices and trends. In recent years, sentiment analysis has been embedded into reinforcement learning for building an algorithmic trading system. This paper is a review paper to analyze and summarize sentiment analysis in reinforcement learning models. Specifically, the paper reviews the data, features, and approaches used in sentiment analysis. To identify the relevant journals and articles, a methodology is applied to review the sentiment analysis in the stock market. These studies are categorized according to their general similarities, differences, limitations, and field to be investigated further. Finally, the last section is the conclusion, which provides the direction for future study.

Sentiment analysis, which stands for opinion mining, is a natural language processing (NLP) technique that involves identifying, extracting, and analyzing sentiments or opinions expressed in text data. The primary goal of sentiment analysis is to determine the sentiment polarity of a given piece of text, whether it is positive, negative, or neutral. This analysis can be applied to various types of content, such as product reviews, social media posts, customer feedback, and news articles. Sentiment analysis algorithms use machine learning and text classification to understand subjective information conveyed in text, helping businesses, organizations, and individuals gain insight into public opinions and emotions about specific topics, products, or services. In this study, we conducted sentiment analysis on a Bengali dataset. For feature extraction, we implemented the term frequency-inverse document frequency (TF-IDF) technique, and for feature selection, we applied an extra tree classifier approach. Subsequently, we trained our machine learning model, achieving an impressive accuracy rate of 92%.

The computational process of identifying and categorizing opinions that are expressed in the piece of text could be employed to determine information insight and the writer's opinion toward a particular topic. Most sentiment analysis employed for English text. Contrarily, a plethora method for sentiment analysis has been reported that the task stayed an interesting question for Indonesian text. The invention of machine learning models and broad accessibility of Twitter data on previous years have derived many researchers to take a machine learning model to resolve the sentiment analysis problem. The objective of this study is to build a sentiment analysis model using Sentiwordnet and machine learning for Indonesia general election opinion in Indonesian text from the twitter content. The data of the tweet was taken namely, the username, and the tweet itself. The theme of the tweet was the topic related to the 2019 general election figures, namely Joko Widodo and Prabowo Subianto. The period of data collection was November 13, 2018, to January 11, 2019, during the campaign period. The tweet was in Indonesia language. The result revealed sentiment analysis with the Naïve Bayes classification method showed 74.94% accuracy for Joko Widodo topic, while 71.37% accuracy for Prabowo topic.

Social networking sites and micro blogs provide tremendous amount of real time data every day. Sentiment analysis or opinion mining aims to automate the process of sentiment extraction from the user content available online. Twitter in recent years due to its high subscriber rate and diverse audience, has become increasingly powerful in representing and changing user opinions over an object or event. This paper focuses on research conducted within the field of twitter sentiment analysis. The objective is to comprehensively investigate the task of sentiment analysis and its sub processes and identify the different tools, techniques or other resources used or applied on twitter data during the process. A Systematic Literature Review (SLR) has been conducted to identify 40 researches, relevant to sentiment identification and analysis. The work presented covers major tools and techniques used during sentiment mining process and maybe utilized by researchers or practitioners for identifying potential research directions as well as suggest possible software development areas that need to be explored.

In this study, we explore the potential of machine learning (ML) models after different text representation methods on the balanced IMDB dataset, which is widely regarded as a gold standard in sentiment analysis, one of the Natural Language processing (NLP) tasks. On the open source IMDB movie reviews dataset, we first undertake data cleaning and text representation with data preprocessing steps. Then, we apply sentiment classification using different ML models. In order to evaluate the models, we used precision (P), recall (R), F1-score (F1), and area under curve (AUC), as well as receiver operating characteristic (ROC). It is worth noting that text feature extraction with Bidirectional Encoder Representations from Transformers (BERT) provided the highest performance in all models, with the SVM model offering particularly promising results. In this model, we observed the following results: ACC 0.9033, F1 0.9308, R 0.9015, R 0.9015, P 0.9072, AUC 0.9638, and ROC 0.96. These findings suggest that NLP techniques and, in particular, machine learning models that employ BERT may offer high levels of accuracy and reliability in text classification problems. It would be beneficial for future studies to validate these findings using BERT on different NLP tasks. This would help to evaluate the effectiveness and applicability of the models in practice.

Objective: The primary aim of this study is to develop a comprehensive model that can identify and analyze the factors influencing customer engagement with brands. Methodology: A mixed-methods approach was utilized for this purpose. In the qualitative section, interviews were conducted with managers and experts in the field of digital marketing at a dairy company. These interviews aimed to identify and gain a deeper understanding of the key factors that could impact brand engagement on social media. The results of these interviews facilitated the identification of initial and main codes using MaxQDA software. In the quantitative section, a dataset comprising 50,525 user-generated content in response to 505 promotional posts by a dairy brand on Instagram was used. By employing the BERT model and Natural Language Processing (NLP) techniques, the sentiments of users in their comments were analyzed and identified. After sentiment analysis, the K-means clustering technique was employed to organize the sentiments into distinct topics. Subsequently, these clusters were compared and analyzed with expert opinions to identify the most critical factors influencing brand engagement. Findings: The findings of the research indicated that cognitive factors such as brand awareness, emotional factors such as positive emotions and emotional attachment, and behavioral (social) factors such as participation and social interaction each play a vital role individually and interactively in customer engagement and loyalty. Conclusion: This research demonstrated that creating positive emotional experiences and encouraging active participation in social activities can significantly contribute to positive interactions and customer loyalty to the brand.

This study aims to analyze the sentiment of the Hindu community toward religious issues on social media, with a specific focus on Kapuas Regency, Central Kalimantan. The development of social media as a digital public sphere has positioned platforms such as Instagram and Twitter as primary spaces for the spontaneous and open expression of opinions, perceptions, and religious attitudes. This study is important because religious issues in digital spaces often influence social harmony and shape religious discourse within society. The research employs a quantitative approach using text mining and sentiment analysis based on Natural Language Processing (NLP). Primary data were collected through web scraping techniques, utilizing Apify for Instagram and asynchronous Python scripts for Twitter, with relevant keywords, hashtags, and geographic indicators. The analysis process includes text preprocessing (cleaning, tokenization, stopword removal, and stemming), followed by sentiment classification using a lexicon-based approach with the InSet dictionary into three categories: positive, negative, and neutral. The analysis results were evaluated using a confusion matrix, along with precision, recall, and F1-score metrics to assess model reliability. The findings indicate that positive sentiment predominates on both Instagram and Twitter, followed by neutral sentiment, while negative sentiment appears in only a small proportion. Positive sentiment is generally associated with expressions of prayer, gratitude, tolerance, and calls for togetherness, whereas negative sentiment tends to emerge in discussions related to ritual differences or responses to socio-religious controversies. The sentiment analysis model achieved an accuracy of 100% on Instagram data (self-evaluation) and 74.4% on Twitter data (manual evaluation), with relatively high precision and recall values, indicating that the results are statistically reliable.