Sentiment Of Tweets Research Articles

Do Financial Community’s Tweet Sentiments Affect the Stock Market? Evidence from an Emerging Economy

In the era of social media and internet, Twitter (presently ‘X’) has been recognized as the prominent factor for financial markets by multiple corporates and experts. The motivation of present research hinges on burgeoning popularity of Twitter in the financial community for sharing information and impact of their hidden sentiments on financial markets. Research on tweet-based sentiments and their influence on financial markets in India is still in the infancy stage. To cover this gap, the present study empirically investigates the predictive impact of financial tweet sentiments on the Indian stock Index’s returns over a short period. The paper scraped 22,816 tweets and Nifty 50 index’s intraday hour end values for January 2023. Using Natural Processing Technique, the overall sentiments of the financial community are found as highly positive for each trading hour. Next, it presents a low positive correlation between positive sentiments, sentiment polarity, and hourly returns. Lagged negative sentiments reflect the better ability to impact current period returns than positive sentiments and polarity. Additionally, sentiment polarity and returns reflect bi-directional causation for the future period impact. Investors, stock market traders, and other practitioners can employ the proven concept of linkage between tweet sentiments and returns for constructing effective investment and trading strategies. JEL Classifications: G41, D53, G17, G02, G19

Enhancement of The Performance of Machine Learning Algorithms to Rival Deep Learning Algorithms in Predicting Stock Prices.

This paper objectives to improve stock market prediction accuracy by training data on sentiment analysis of tweets, overcoming volatility and complexity. Utilizing the Use of natural language processing (NLP) algorithms, the tweet's sentiments were classified into (negative - neutral - and positive). The stock value price was predicted by implementing Machine learning algorithms (KNN, SVM, GBM, LR, DT, RF, EL). Among the techniques of ML, (GBM) achieved the greatest results in terms of accuracy (96%). Its results were compared with the results of a deep learning algorithm that uses the same data where GBM got better results, and other algorithms showed results (KNN = 55%, SVM=90%, LR=82%, DT=90%, RF=90%, EL = 88%). The results obtained were superior to previous studies.

AraTSum: Arabic Twitter Trend Summarization Using Topic Analysis and Extractive Algorithms

Twitter’s trending topics enable users to view the topics currently being discussed on the platform. Users can stay up to date with news, events, and conversations. However, the platform’s method of sorting tweets by time can make it hard to gather semantic information. To fully comprehend the various dimensions of trends and the diverse opinions surrounding them, users need to sift through a substantial number of results. Traditional techniques for content summarization, such as multi-document summarization, can facilitate information aggregation, categorization, and visualization of events, but there are two challenges. First, they fail to consider the topic’s polarity, which is essential to covering all aspects of the subject and incorporating less popular opinions. Second, some techniques only provide summaries at the topic level, potentially leaving out crucial dimensions that require representation in this summary. This research developed a novel summarization approach on Twitter which is known as ARAbic Trending SUMmarization (AraTSum). The proposed system generates the summary based on the extracted topics and aspects from the trend. The approach involves a topic sentiment-based technique that combines generative statistical Latent Dirichlet Allocation with a pre-trained model to automatically reflect the sentiments (negative or positive) of tweets in each topic; followed by extractive summarization algorithms in each cluster. The AraTSum was evaluated through several experiments on five different X datasets. The obtained results showed that AraTSum outperformed existing approaches on the ROUGE evaluation metric compared to state-of-the-art Twitter event summarizing algorithms. To ensure a comprehensive and accurate evaluation, three human experts were tasked with manually summarizing the utilized five datasets. The results demonstrated that the proposed AraTSum method is dependent on sentiment topical aspect analysis, and it enhances the summarization's performance.

Social sharing of emotion during the collective crisis of COVID-19.

We collected data from two sources - social media and online questionnaires - to investigate the emotional consequences of social sharing during the COVID-19 pandemic. Study 1 tracked and analysed sentiment of tweets posted over the course of a month in the crisis period and found that users who tweeted more frequently about COVID-19 expressed decreasing negative sentiment and increasing positive sentiment over time. Granger causality tests confirmed that this association was better interpreted in the forward direction (sharing levels predicting sentiment) than in the reverse direction (sentiment predicting sharing levels). Study 2 focused on immediate emotional consequences of sharing COVID-19-related events and found that participants reported improved overall affect about an event after sharing it, especially when that event was a personal experience rather than a news story. Reported positive feelings about both kinds of events were also significantly higher after sharing. Taken together, both studies suggested that social sharing is linked with emotional relief and may therefore help people to deal with their negative experiences during a persistent collective crisis.

Stock prediction using Bi-LSTM and RoBERTa sentiment analysis

Stock price forecasting is a widespread research issue in the field of finance. Stock price prediction can give investors more accurate advice and yield higher returns. With the popularity of social media, more and more people choose to express their opinions, and more and more media outlets published news on social media. This paper mainly conducts stock analysis and prediction by presenting the RoBERTa-BiLSTM model with the Bahdanau attention mechanism. It consists of two existing models: the RoBERTa and bidirectional LSTM models. The experimental results show that this model is more accurate in predicting stock prices than the Multi-Layer Perception (MLP) and LSTM models. Inputs to the model include historical AAPL stock price data and sentiment data analysed by news and Twitter tweet sentiment. In this paper, the high-precision RoBERTa-BiLSTM model for stock prediction was proposed, which provides a solution for stock prediction. The practical applications and the typical problem of most studies about stock prediction called the time-shifted problem, are provided in this paper and also have research value.

Classification of supervised deep learning models for COVID-19 tweets sentiment analysis

Social media provided a successful management of human societies in light of global crises. Social media platforms have been considered the central authority in guiding society, receiving information and conducting business in many countries during the COVID-19 pandemic period in March 2020. The social platform has seen an increase in use of 45% for public platforms and 35% for the use of messages. This study suggests An AI-based model for predicting the likelihood of infection with COVID-19 through sentiment analysis and early detection using a Natural Language Processing library with deep learning techniques CNN. The model performed improved the distinction between patients who are 'positive' and patients who are 'natural' and unaffected are 'negative'. The performance of the model was tested using publicly available databases on Twitter for the period from March 16, 2020 to April 14, 2020.The achieved accuracy percentage was (~99.8% )) and based on the four measures Accuracy, Recall, Precision and F1-score.

Comparative Study among Term Frequency-Inverse Document Frequency and Count Vectorizer towards K Nearest Neighbor and Decision Tree Classifiers for Text Dataset

Background: Text classification techniques are increasingly important with the exponential growth of textual data on the internet. Term Frequency-Inverse Document Frequency (TF-IDF) and Count Vectorizer(CV) are commonly used methods for feature extraction. TF-IDF assigning weights to terms based on their frequency. CV simply counts the occurrences of terms. The performance of CV as well as TF-IDF are evaluated and compared with KNN and DT classifiers across text datasets. Methodology: The investigation begins with preprocessing. The feature vectors are created using both TF-IDF and CV. Feature vectors are passed into the KNN and DT classifiers at in training stage. Experiments are executed the usage of Kaggle's public database Ukraine 10K tweets sentiment_analysis dataset and the Womens ecommerce clothing reviews dataset. Findings: The average of precision, recall, f1 score and accuracy of KNN with TF-IDF were 84.5%, 87%, 83%, 87% respectively and KNN with CV were 83.5%, 87%, 83.5%, 87% respectively. Similarly, average of precision, recall, f1 score and accuracy of DT with TF-IDF were 89%, 89%, 89%, 89% respectively and DT with CV were 89%, 89.5%, 89.5%, 89.5% respectively. The results obtained in this research is consistent with previous similar research result. Conclusions: The performance of TF-IDF is almost similar as CV for a particular dataset and a particular classifier in this study. Novelty: The experiment performed using these classifiers and feature extraction methods on the datasets is a novelty and contribution of this research.

Examining Implications of Search Query Construction on Sentiment Analysis: The Case of Brandwatch

Consistent with other fields, advertising research is currently facing a replication crisis, evoking methodological concerns regarding the reproducibility of research findings. To address this crisis, we systematically reviewed seven computational advertising studies that collected and analyzed the sentiment of tweets. Upon identifying five studies that reported replicable data collection processes, we utilized the original search queries to recollect tweets using a third-party platform, Brandwatch. We also replicated data collection using iterative complex Boolean (ICB) operators, which sought to enhance the resulting dataset precision. Then, we juxtaposed the effects of search query design (original vs. ICB) using sentiment analysis. Together, the findings suggest that how a query is written can affect measures of precision, engagement, sentiment, and recall. Tests of precision are recommended to mitigate the effects of variance in retrieval relevance.

Analysis of Sentiment Based on Opinions from the 2019 Presidential Election

Twitter is a popular social media platform where the public is free to comment and write about anything. It is common for people to post comments containing harsh words and even hate speech. The 2019 presidential election in Indonesia generated a significant amount of comments, with some users praising the candidates, others criticizing them, and some even resorting to insults. To extract meaningful information from these comments and classify the text, sentiment analysis is essential. In this research, sentiment analysis involves the process of categorizing textual documents into two classes: negative and positive sentiment. The opinion data was collected from the Twitter social network in the form of tweets related to the 2019 presidential election. The dataset used in the study consisted of 3,337 tweets, which were divided into 70% training data and 30% test data. The training data comprised tweets whose sentiment was already known, serving as a foundation for the model to learn and make predictions. The primary objective of this research is to determine whether the tweets, written in Indonesian, express positive or negative sentiments. The Naive Bayes Classifier algorithm was employed to classify the tweet data. This algorithm is well-suited for text classification tasks due to its simplicity and efficiency in handling large datasets. The classification results on the test data demonstrated that the Naive Bayes Classifier algorithm achieved an overall accuracy of 71%. Specifically, the accuracy for negativesentiment classification was 71%, while the accuracy for positive sentiment classification was 70%. These results indicate that the Naive Bayes Classifier is effective in distinguishing between positive and negative sentiments in tweets related to the presidential election

Twit-CoFiD: a hybrid recommender system based on tweet sentiment analysis

Twit-CoFiD: a hybrid recommender system based on tweet sentiment analysis

Analisis Sentimen Twitter Terpilihnya Prabowo - Gibran Menggunakan Metode Neural Network

One of the most important elections in Indonesian democracy is the presidential election, which chooses the country's leader for the next five years. In the 2024 presidential election, there are three candidates for president and vice president, including the Prabowo Subianto - Gibran Rakabuming Raka pair. The election process has taken centre stage on social media, particularly Twitter, where people interact, share information, and express their opinions and feelings. This study aims to look at public opinion towards the Prabowo-Gibran team, which has attracted a lot of attention since Gibran was nominated as a vice presidential candidate until he was declared the winner in the 2024 presidential election by the KPU. This analysis provides valuable insight into understanding public opinion and feelings towards the president and vice president-elect. The method used in this research is neural network (NN), which is proven to be effective in text data classification and capable of producing high accuracy. The dataset used is public opinion on Twitter, which is taken through the data crawling process. The initial data of 1511 tweets was then cleaned and prepared into a dataset of 1500 tweets, with the main attribute being the content of the tweet. Based on the findings, the neural network model created was able to classify the sentiment of tweets related to the Prabowo-Gibran pair with an accuracy rate of 93%. Thus, this sentiment analysis makes an important contribution to understanding the public's response to the presidential election process and the election of a new president and vice president

Persistence of misinformation and hate speech over the years: The Manchester Arena bombing

In the aftermath of the 2017 Manchester Arena bombing, the ensuing debate in the press and on social media underscored terrorism's potential to intensify divisions. This study delves into the social media and press dynamics of rumors following the attack, and into the subsequent discourse on migration policies. We collected a dataset consisting of 3184 press articles and 89,148 tweets about the Manchester Arena bombing. This research aims to identify prevalent rumors, explore the short- and long-term impacts on user engagement, analyze the sentiment in tweets related to each rumor, and examine perceptions of terrorism threats and migration policies among both the press and X (previously Twitter) users. The study found that X acted as an echo chamber for misinformation, amplifying specific rumors related to the attack, while the press exhibited fact-checking practices and provided nuanced perspectives. Notably, one rumor suggesting the attacker was a refugee gained traction over the years, reflecting an increase in anti-immigrant sentiments. Emotional responses on X ranged from neutral to heightened distress and anger, highlighting the significant impact of social media narratives on public sentiment. The research underscores the polarization of views on social media, influenced by the condensed format of tweets and the rapid production cycle, with X users expressing predominantly very negative attitudes toward immigration. This study emphasizes the critical role of the media in dispelling misinformation and fostering nuanced public understanding in complex sociopolitical contexts.

Analisis Sentimen Ibu Kota Nusantara menggunakan Algoritma Support Vector Machine dan Naïve Bayes

The Government's policy of moving the Indonesian capital city (IKN) is considered controversial, sparking various responses from the public, especially on the social media platform X. This research aims to analyze tweet sentiment related to IKN and compare two algorithms. In this experiment, we collected 5,128 tweets regarding IKN from the X application. The dataset was classified into 2,598 positive sentiments and 1,659 negative sentiments. To analyze these sentiments, we used Text Mining techniques, comparing the Support Vector Machine (SVM) and Naive Bayes algorithms. To improve the performance of these algorithms in analyzing the data, SMOTE optimization was employed to address data imbalance. Our findings show that the SVM algorithm achieves an accuracy of 84%, while the Naive Bayes algorithm achieves an accuracy of 77%. Thus, it can be concluded that the SVM algorithm is superior to the Naive Bayes algorithm. Furthermore, the use of SMOTE optimization proved to enhance the ability of both algorithms to identify positive sentiment, as evidenced by the precision, recall, and F1-Score values. The SVM algorithm achieved a precision of 82%, recall of 86%, and F1-Score of 84%, while the Naive Bayes algorithm achieved a precision of 71%, recall of 92%, and F1-Score of 80%.

Comparing the accuracy of ANN with transformer models for sentiment analysis of tweets related to COVID-19 Pfizer vaccines

The current study underscores the critical importance of understanding public sentiment towards vaccination efforts, particularly to achieve the widespread vaccine uptake necessary for public health security, especially in light of pandemics like COVID-19. Despite the clear critical role vaccinations play in mitigating pandemic spread, vaccine hesitancy persists as a formidable challenge. This research focuses on analyzing sentiments related to the Pfizer-BioNTech COVID-19 vaccine using Natural Language Processing (NLP) techniques, offering a comparative assessment of Artificial Neural Network (ANN) frameworks and transformer-based models. The study employs the Valence Aware Dictionary and sEntiment Reasoner (VADER) for sentiment quantification and TensorFlow for text vectorization. Within the ANN domain, both Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models are investigated, alongside the ALBERT and Distilbert models as a representative of transformer-based architectures. The empirical analysis reveals a distinct advantage of transformer-based models over ANN frameworks in accuracy, with the ALBERT model exhibiting exceptional skill in classifying sentiments of tweets concerning the COVID-19 vaccine by Pfizer. The study meticulously employs Receiver Operating Characteristic (ROC) curve analysis to rank the performance of the evaluated models in sentiment classification, establishing ALBERT as the foremost model, followed in order by LSTM-CNN, Distilbert, CNN, and LSTM models. The ALBERT model demonstrates outstanding performance across critical evaluation metrics. The findings advocate for the strategic use of advanced NLP technologies in public health initiatives to better understand and respond to public attitudes towards vaccination, ultimately contributing to improved health outcomes and pandemic preparedness.

Who shows more emotion when interacting with a company on social media? A study of political orientation and tweet sentiment

This study provides insights into how consumers interact with companies on social media. The study draws upon the theory of personality and political orientation to examine the relationship between consumers’ political orientation and the emotion used in their online interactions with companies. To provide additional understanding of this relationship, the study incorporates the political orientation of companies as a moderator. Leveraging Twitter (now known as ‘X’) as a research context, the study provides empirical evidence that more conservative consumers show less positive emotion when interacting with companies. The findings suggest that this relationship is weaker when the company involved has a more conservative (or less liberal) political orientation. Finally, the main effect follows a non-linear pattern that becomes stronger at an exponential rate among the most conservative consumers.

Enhancing online learning: sentiment analysis and collaborative filtering from Twitter social network for personalized recommendations

Online learning presents a major challenge for learners, namely the diversification of courses and information overload. In response to this issue, recommender systems are widely used. Nowadays, social networks have become a global platform where individuals share a multitude of information. For instance, Twitter is a social network where users exchange messages and interact with various communities. These interactions on social networks have created a new dimension in the field of online learning. In this article, we propose a novel approach that combines sentiment analysis of learners’ reviews on social networks with collaborative filtering methods to provide more personalized and relevant course recommendations. To achieve this, we explored different models to analyze the sentiments of tweets related to online courses. Additionally, we used collaborative filtering based on k-nearest neighbors (KNN). Our results demonstrate that integrating sentiment analysis provides more relevant recommendations. This has also been shown based on the calculation of root mean square error (RMSE) compared to a traditional approach. In this study, we demonstrated that by leveraging this information from social networks like Twitter, online learning platforms can enhance the effectiveness of their course recommendations, tailoring them to each individual learner’s needs.

Deep learning based Election Results Prediction using Twitter Data

Abstract: This project presents an intelligent system political sentiment analysis with information from Twitter. . The system utilizes deep learning techniques, specifically a BiLSTM model featuring an attention mechanism, to predict the political affiliation (BJP or Congress) of tweets. The data preprocessing involves cleaning text, data augmentation, tokenization, and indexing. A dataset is used to train the model. consisting of tweets from both parties, getting very accurate results in predicting the sentiment of tweets. Additionally, the software offers functionality for data visualization, including displaying sample tweets, sentiment analysis results, and the winning party. Additionally, an admin page is available for further customization and management. Overall, this project the possibilities of Using deep learning to analyze sentiment of political content on social media data.

Analytical Study for Prjice Prediction of Bitcoin Using Machine Learning and Artificial Intelligence

Abstract: Cryptocurrency transactions rely on encryption algorithms for security and decentralization. However, traditional machine learning algorithms often struggle with the dynamic cryptocurrency market, leading to inaccuracies. To address this, integrating Integrating sentiment analysis of Twitter data alongside Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU) models enriches the analysis of cryptocurrency market dynamics. Twitter provides dataset from kaggle open source and the sentiment expressed by users on cryptocurrencies, enabling the prediction of tweet sentiment (positive, negative, or neutral) through Natural Language Processing (NLP). This integration enhances understanding of market sentiment's impact on cryptocurrency prices: positive sentiment may drive prices up, negative sentiment may lead to declines, and neutral sentiment may indicate stability. By analyzing sentiment alongside historical trends and emerging patterns, users gain a holistic view of cryptocurrency markets. This approach aids decision-making, improving transaction accuracy and efficiency. Ultimately, the combination of sentiment analysis with BiLSTM and BiGRU models advances the comprehension of cryptocurrency market dynamics, enhancing user insights and facilitating informed decisions in the volatile cryptocurrency ecosystem.

How Do Teachers Collaborate in Informal Professional Learning Activities? An Epistemic Network Analysis

Teachers turn to many sources for support and professional learning, including social media-based communities that have shown promise to help teachers access resources and facilitate productive exchanges. Although such online communities show promise, questions about their quality for providing a suitable learning environment remain insufficiently answered. In this study, we examine how teachers’ engagement on Twitter (now known as “X”) may adhere to characteristics of high-quality professional development (PD) activities. In that, we employ advanced conversational analysis techniques that extend the primarily descriptive methods used in prior research. Specifically, we collected data from three Twitter communities related to Advanced Placement Biology (N = 2,040 tweets, N = 93 teachers). Qualitative two-cycle content analyses derived both tweet content and sentiment. Using epistemic network analyses, we examined the collaborative structures to examine how participation patterns can identify characteristics of high-quality online PD. Results indicate that some teachers use Twitter with a content focus and coherent to their individual contexts and prior knowledge. Notably, differences in collaboration and participation patterns by teachers’ overall activity level hint at the existence of an online community of practice. More active teachers communicated more about how their individual contexts relate to instruction, whereas less active teachers exhibited more targeted engagement, for instance, related to sharing teaching resources and organizing learning opportunities. Overall, this study illustrates how Twitter may provide a meaningful learning environment to teachers so that it can serve as a relevant avenue for their professional learning.

Deep learning in finance assessing twitter sentiment impact and prediction on stocks

The widespread adoption of social media platforms has led to an influx of data that reflects public sentiment, presenting a novel opportunity for market analysis. This research aims to quantify the correlation between the fleeting sentiments expressed on social media and the measurable fluctuations in the stock market. By adapting a pre-existing sentiment analysis algorithm, we refined a model specifically for evaluating the sentiment of tweets associated with financial markets. The model was trained and validated against a comprehensive dataset of stock-related discussions on Twitter, allowing for the identification of subtle emotional cues that may predict changes in stock prices. Our quantitative approach and methodical testing have revealed a statistically significant relationship between sentiment expressed on Twitter and subsequent stock market activity. These findings suggest that machine learning algorithms can be instrumental in enhancing the analytical capabilities of financial experts. This article details the technical methodologies used, the obstacles overcome, and the potential benefits of integrating machine learning-based sentiment analysis into the realm of economic forecasting.