Twitter API Research Articles

Tracking social provenance in chains of retweets

In the era of massive sharing of information, the term social provenance is used to denote the ownership, source or origin of a piece of information which has been propagated through social media. Tracking the provenance of information is becoming increasingly important as social platforms acquire more relevance as source of news. In this scenario, Twitter is considered one of the most important social networks for information sharing and dissemination which can be accelerated through the use of retweets and quotes. However, the Twitter API does not provide a complete tracking of the retweet chains, since only the connection between a retweet and the original post is stored, while all the intermediate connections are lost. This can limit the ability to track the diffusion of information as well as the estimation of the importance of specific users, who can rapidly become influencers, in the news dissemination. This paper proposes an innovative approach for rebuilding the possible chains of retweets and also providing an estimation of the contributions given by each user in the information spread. For this purpose, we define the concept of Provenance Constraint Network and a modified version of the Path Consistency Algorithm. An application of the proposed technique to a real-world dataset is presented at the end of the paper.

Implementation of Naïve Bayes in the Analysis of Public Sentiment on Twitter for Shopee's Flash Sale

Rumors spread among the public that there was fraud occurring during the ongoing flash sale Shopee process. In order to answer the problems found, this study aims to find out how the public feels about the flash sale activity. Data was taken using the Twitter API, and the tweets used started from January 2021–June 2021. As a result, there were 3,467 Twitter data points. After passing through the text preprocessing stage, the data becomes clean data, which amounts to 457. The research results obtained using the Nave Bayes Classifier method show the results of public opinion on Twitter with positive sentiment categories of 19.4%, negative sentiment categories of 43.1%, and neutral sentiment categories of 37.4%, with an accuracy rate of 98%.

Twitter Bot Detection Using Diverse Content Features and Applying Machine Learning Algorithms

A social bot is an intelligent computer program that acts like a human and carries out various activities in a social network. A Twitter bot is one of the most common forms of social bots. The detection of Twitter bots has become imperative to draw lines between real and unreal Twitter users. In this research study, the main aim is to detect Twitter bots based on diverse content-specific feature sets and explore the use of state-of-the-art machine learning classifiers. The real-world data from Twitter is scrapped using Twitter API and is pre-processed using standard procedure. To analyze the content of tweets, several feature sets are proposed, such as message-based, part-of-speech, special characters, and sentiment-based feature sets. Min-max normalization is considered for data normalization and then feature selection methods are applied to rank the top features within each feature set. For empirical analysis, robust machine learning algorithms such as deep learning (DL), multilayer perceptron (MLP), random forest (RF), naïve Bayes (NB), and rule-based classification (RBC) are applied. The performance evaluation based on standard metrics of precision, accuracy, recall, and f-measure reveals that the proposed approach outperforms the existing studies in the relevant literature. In addition, we explore the effectiveness of each feature set for the detection of Twitter bots.

The Perception and Usage of Fake Braces: Twitter Content Analysis

Introduction: Financial concerns deter many people from seeking orthodontic care. Fake braces replicate the real orthodontic braces but are not functional and are priced at a lower cost. These products are available through illegal and unregistered merchants, who use social media for advertising their products. This study aimed to analyze Arabic Twitter posts related to fake braces. Methods: Tweets were collected from Twitter API v2 using Python. The search was limited to the Arabic language, using keywords such as “fake braces” and “fashion braces.” Tweets were collected in the period from January 1, 2020, until July 31, 2021. Both sentiment and thematic analyses were performed. Results: 788 tweets met the inclusion criteria, 660 of which were advertisements. The rest of the tweets (n = 128) were categorized into four main themes: rejecting the idea of fake braces (49.2%), having the intention to buy fake braces (32.0%), using/used fake braces (14.1%), and accepting the idea of fake braces (4.7%). Sentiment analysis showed that more than half of the tweets (55.5%) were negative and mainly involved sarcastic language (65.8%). Conclusion: Although many of the tweets were against the use of fake braces, a sizable number of advertisement tweets promoted fake braces. Efforts should be made to educate the public about the risks of using fake braces and to emphasize the importance of seeking a licensed orthodontist for treatment. In addition, health authorities must establish laws and policies and enhance surveillance to control social media content advertising these harmful products.

Twitter Sentiment Analysis

Twitter Sentiment Analysis is the process of extracting opinions, sentiments, and emotions expressed in tweets. This analysis can be used to determine the overall public opinion on a particular topic or to gauge the sentiment of customers towards a product or service. We use Textblob to classify tweets as positive, negative or neutral based on their content. We start by collecting a dataset of tweets using the Twitter API and manually labelling them as positive, negative or neutral. We are doing preprocess the text by removing stop words, punctuation, and special characters, and convert the text into a bag-of-words representation. We then use Textblob to train a model on the preprocessed data and test it on a separate set of tweets. Keyword: Textblob, twitterdataset, Twitter sentiment analysis

Sentiment Analysis of Twitter Cases of Riots at Kanjuruhan Stadium Using the Naive Bayes Method

Sentiment analysis is a process carried out to analyze opinions, sentiments, judgments, and emotions from the riot case at the kanjuruhan stadium. The purpose of this research is to find out public opinion about the tragedy that is currently happening at the Kanjuruhan Stadium. the data was obtained from social media Twitter using the Twitter API, then after that, an analysis was carried out. data from the results of the analysis will be classified using the Naive Bayes method. The classification process is divided into 7 (seven) stages, namely Crawling, Cleansing, pre-processing, labeling, classification, data training, and data testing. In the labeling process, data is classified into 2 (two) classes, namely the positive class and the negative class. The data obtained before the preprocessing process was 1963 tweets, after the preprocessing the data obtained was 1001 tweets. The data will be trained and tested using the naive Bayes classification method. classification results obtained precision values of 82% for negative data and 65% for positive data, recall values obtained 74% for negative data and 75% for positive data, F1-score values obtained 78% for negative data and 70% for positive data, while accuracy value obtained 74%.

SEBD: A Stream Evolving Bot Detection Framework with Application of PAC Learning Approach to Maintain Accuracy and Confidence Levels

A simple supervised learning model can predict a class from trained data based on the previous learning process. Trust in such a model can be gained through evaluation measures that ensure fewer misclassification errors in prediction results for different classes. This can be applied to supervised learning using a well-trained dataset that covers different data points and has no imbalance issues. This task is challenging when it integrates a semi-supervised learning approach with a dynamic data stream, such as social network data. In this paper, we propose a stream-based evolving bot detection (SEBD) framework for Twitter that uses a deep graph neural network. Our SEBD framework was designed based on multi-view graph attention networks using fellowship links and profile features. It integrates Apache Kafka to enable the Twitter API stream and predict the account type after processing. We used a probably approximately correct (PAC) learning framework to evaluate SEBD’s results. Our objective was to maintain the accuracy and confidence levels of our framework to enable successful learning with low misclassification errors. We assessed our framework results via cross-domain evaluation using test holdout, machine learning classifiers, benchmark data, and a baseline tool. The overall results show that SEBD is able to successfully identify bot accounts in a stream-based manner. Using holdout and cross-validation with a random forest classifier, SEBD achieved an accuracy score of 0.97 and an AUC score of 0.98. Our results indicate that bot accounts participate highly in hashtags on Twitter.

Halal or Haram? The COVID-19 Vaccine Discussion Among Twitter users in Malaysia.

Vaccine hesitancy is gaining attention due to the increasing spread ofthe COVID-19 pandemic in Malaysia. Malaysia is a majority Muslim country and religion has a significant influence on the acceptance or rejection of vaccines. This is clearly seen through the disagreement over the halal statusof vaccines. Social media has become a platform for discussion and dissemination of information and dis-information on vaccines. Thus, it has had a relatively significant influence on vaccine hesitancy among social media users. By analysing tweets from February 2020 to February 2021 using Twitter API, this paper highlights the discussion of COVID-19 vaccines' halal status on Twitter. This study focuses on the analysis of vaccination reluctancy among the Twitter users in Malaysia and found that the most prevalent theme from the discussion is the constructed religious narratives to justify scientifically misleading and false claims concerning vaccination represented on social media. This finding also calls for a deeper understanding of society's constructed knowledge concerning contemporary issues in the digital age on social media.

The Perception and Usage of Fake Braces: Twitter Content Analysis

Introduction: Financial concerns deter many people from seeking orthodontic care. Fake braces replicate the real orthodontic braces but are not functional and are priced at a lower cost. These products are available through illegal and unregistered merchants, who use social media for advertising their products. This study aimed to analyze Arabic Twitter posts related to fake braces. Methods: Tweets were collected from Twitter API v2 using Python. The search was limited to the Arabic language, using keywords such as “fake braces” and “fashion braces.” Tweets were collected in the period from January 1, 2020, until July 31, 2021. Both sentiment and thematic analyses were performed. Results: 788 tweets met the inclusion criteria, 660 of which were advertisements. The rest of the tweets (n = 128) were categorized into four main themes: rejecting the idea of fake braces (49.2%), having the intention to buy fake braces (32.0%), using/used fake braces (14.1%), and accepting the idea of fake braces (4.7%). Sentiment analysis showed that more than half of the tweets (55.5%) were negative and mainly involved sarcastic language (65.8%). Conclusion: Although many of the tweets were against the use of fake braces, a sizable number of advertisement tweets promoted fake braces. Efforts should be made to educate the public about the risks of using fake braces and to emphasize the importance of seeking a licensed orthodontist for treatment. In addition, health authorities must establish laws and policies and enhance surveillance to control social media content advertising these harmful products.

An NLP-assisted Bayesian time-series analysis for prevalence of Twitter cyberbullying during the COVID-19 pandemic.

COVID-19 has brought about many changes in social dynamics. Stay-at-home orders and disruptions in school teaching can influence bullying behavior in-person and online, both of which leading to negative outcomes in victims. To study cyberbullying specifically, 1 million tweets containing keywords associated with abuse were collected from the beginning of 2019 to the end of 2021 with the Twitter API search endpoint. A natural language processing model pre-trained on a Twitter corpus generated probabilities for the tweets being offensive and hateful. To overcome limitations of sampling, data were also collected using the count endpoint. The fraction of tweets from a given daily sample marked as abusive is multiplied to the number reported by the count endpoint. Once these adjusted counts are assembled, a Bayesian autoregressive Poisson model allows one to study the mean trend and lag functions of the data and how they vary over time. The results reveal strong weekly and yearly seasonality in hateful speech but with slight differences across years that may be attributed to COVID-19.

Aspect Based Sentiment Analysis and Opinion Mining on Twitter Data Set Using Linguistic Rules

Objectives: To propose the most effective machine learning technique for aspect based sentiment analysis of consumer feedback reviews by correlating people’s emotions of different aspects of a product or service with word importance, linguistic rules, tagging, dependency relations and filtering to enhance the classification accuracy and to explore the different machine learning approaches in order to determine their significance and to spark interest in this field of study. Methods: The dataset has been taken from the most popular networking site twitter using twitter API. A total of 33,036 tweets were retrieved for this study from16 July 2022 to 16 Sept. 2022, but were only able to include 7570 tweets after data cleaning and then proposes a model named SVMS (SVM using Spacy) for sentiment Analysis. To measure the performance of a particular model, numerous analyses are conducted on the dataset and then the effectiveness of proposed model is compared with 4 basic classifiers LR, NB, RF and SVM. The parameters used in this study are accuracy, precision, recall, and F1 score. Findings: It is found that the Proposed SVMS model shows better results than all other algorithms by having 96% accuracy which is 1% faster than LR, 2% faster than NB, 5% faster than RF, and 4% faster than SVM, 96% precision, 98% recall and 97% F1 score. SVMS is recommended in this research context for the classification of the text and has a great significance for future researchers in sentences and text classification. Novelty: In this paper the performance of sentiment analysis classifiers is evaluated. In addition to general opinions, the work examines specific aspects such as product, quality, service, price, and ease of use. Comparing the proposed model with the existing models, it has been found that it outperformed the other models in most of the aspects. Keywords: Aspect; Sentiment Analysis; NLP; Spacy; Linguistics

Textual Feature Extraction Using Ant Colony Optimization for Hate Speech Classification

Feature selection and feature extraction have always been of utmost importance owing to their capability to remove redundant and irrelevant features, reduce the vector space size, control the computational time, and improve performance for more accurate classification tasks, especially in text categorization. These feature engineering techniques can further be optimized using optimization algorithms. This paper proposes a similar framework by implementing one such optimization algorithm, Ant Colony Optimization (ACO), incorporating different feature selection and feature extraction techniques on textual and numerical datasets using four machine learning (ML) models: Logistic Regression (LR), K-Nearest Neighbor (KNN), Stochastic Gradient Descent (SGD), and Random Forest (RF). The aim is to show the difference in the results achieved on both datasets with the help of comparative analysis. The proposed feature selection and feature extraction techniques assist in enhancing the performance of the machine learning model. This research article considers numerical and text-based datasets for stroke prediction and detecting hate speech, respectively. The text dataset is prepared by extracting tweets consisting of positive, negative, and neutral sentiments from Twitter API. A maximum improvement in accuracy of 10.07% is observed for Random Forest with the TF-IDF feature extraction technique on the application of ACO. Besides, this study also highlights the limitations of text data that inhibit the performance of machine learning models, justifying the difference of almost 18.43% in accuracy compared to that of numerical data.

Location-based Sentiment Analysis of 2019 Nigeria Presidential Election using a Voting Ensemble Approach

Nigeria president Buhari defeated his closest rival Atiku Abubakar by over 3 million votes. He was issued a Certificate of Return and was sworn in on 29 May 2019. However, there were claims of widespread hoax by the opposition. The sentiment analysis captures the opinions of the masses over social media for global events. In this paper, we use 2019 Nigeria presidential election tweets to perform sentiment analysis through the application of a voting ensemble approach (VEA) in which the predictions from multiple techniques are combined to find the best polarity of a tweet (sentence). This is to determine public views on the 2019 Nigeria Presidential elections and compare them with actual election results. Our sentiment analysis experiment is focused on location-based viewpoints where we used Twitter location data. For this experiment, we live-streamed Nigeria 2019 election tweets via Twitter API to create tweets dataset of 583816 size, pre-processed the data, and applied VEA by utilizing three different Sentiment Classifiers to obtain the choicest polarity of a given tweet. Furthermore, we segmented our tweets dataset into Nigerian states and geopolitical zones, then plotted state-wise and geopolitical-wise user sentiments towards Buhari and Atiku and their political parties. The overall objective of the use of states/geopolitical zones is to evaluate the similarity between the sentiment of location-based tweets compared to actual election results. The results reveal that whereas there are election outcomes that coincide with the sentiment expressed on Twitter social media in most cases as shown by the polarity scores of different locations, there are also some election results where our location analysis similarity test failed.

Sentiment Analysis From Twitter About Covid-19 Vaccination in Indonesia Using Naive Bayes and Xgboost Classifier Algorithm

The pandemic that hit the world has greatly impacted our life. But after some time, it seems that it will be going to end because the vaccine has already been made. In response to this, some people expressed their opinions about this vaccination on social media, for example, in the form of tweets on Twitter. The authors use those opinions or tweets as sentiment analysis material to determine the assessment of this vaccination. The tweet data in this study was obtained through data crawling using the Twitter API with the Python programming language. The variables used in this case are public tweets and their sentiments. This sentiment analysis process uses the Classification method with the Naive Bayes Classifier and will be compared with the XGBoost Classifier algorithm. The results of this study indicate that people are more likely to respond positively to this vaccination. In this case, the Naive Bayes Classifier got better performance with 0.95 from ROC - AUC Score and 134 ms in runtime compared to the XGBoost Classifier algorithm with 0.882 in ROC - AUC Score and 1 minute and 59 seconds in runtime.

Generative Adversarial Networks Classifier Optimized with Water Strider Algorithm for Fake Tweets Detection

In this manuscript, a deep learning-based Generative Adversarial Networks (GAN) classifier optimized with the Water Strider Optimization Algorithm (WSOA) is proposed to solve the issue of fake tweets in Twitter. Initially, input Twitter data is taken from the “Twitter API” dataset. Then, pre-processing is done in the Twitter dataset. After that, the pre-processed tweet features are selected based on the Bag of Words model, mutual information, and the Chi-square method. Then the selected features are given into the Generative Adversarial Networks classifier for detecting fake tweets. Here, the Generative Adversarial Networks classifier is used to fake tweets detection. But it does not expose any optimization strategies adopted to determine the optimum parameters to confirm the accurate categorization of fake tweets. Therefore, Water Strider Optimization Algorithm is applied to optimize the parameter in Generative Adversarial Networks classifier (FT-GAN-WSOAC). The proposed method is activated in MATLAB and the performance is analyzed with performance metrics. The experimental results show that the proposed FT-GAN-WSOA classifier provides higher accuracy of 25.14%, 25.21%, 20.44%, and 34.38% than the existing methods, such as fake tweet detection with content-based features using a custom rule-based algorithm (FT-CBF-CRBA) method, fake tweet detection with long/short-term memory using a random forest algorithm (FT-LSTM-RFA) method, fake tweet detection with zero-shot learning using bidirectional encoder representations from transformers (FT-ZSL-BERT) method, and fake tweet detection with a hybrid convolution neural network and recurrent neural network with long/short-term memory (FT-Hyb CNN-RNN-LSTM) method, respectively.

Using HyperLogLog to Prevent Data Retention in Social Media Streaming Data Analytics

Social media data are widely used to gain insights about social incidents, whether on a local or global scale. Within the process of analyzing and evaluating the data, it is common practice to download and store it locally. Considerations about privacy protection of social media users are often neglected thereby. However, protecting privacy when dealing with personal data is demanded by laws and ethics. In this paper, we introduce a method to store social media data using the cardinality estimator HyperLogLog. Based on an exemplary disaster management scenario, we show that social media data can be analyzed by counting occurrences of posts, without becoming in possession of the actual raw data. For social media data analyses like these, that are based on counting occurrences, cardinality estimation suffices the task. Thus, the risk of abuse, loss, or public exposure of the data can be mitigated and privacy of social media users can be preserved. The ability to do unions and intersections on multiple datasets further encourages the use of this technology. We provide a proof-of-concept implementation for our introduced method, using data provided by the Twitter API.

Examining the differences between human and bot social media accounts: A case study of the Russia-Ukraine War

In this study, we examined online conversations on Twitter about the Russia-Ukraine War and investigated differences between bots and non-bots accounts. Using ‘Russia’ and ‘Ukraine’ as keywords, we employed a Twitter API to collect data from 17 February to 18 March on Twitter. We obtained a large dataset of over 3.7 million tweets generated by about one million distinct accounts. We then analyzed one percent of the data using interval sampling for bot detection and found that about 13.4 percent of the accounts were social media bots, responsible for about 16.7 percent of the tweets. We examined the difference between bots and non-bots regarding online conversations on the Russia-Ukraine War through account analysis, textual analysis, and interaction analysis. The results show that bots exist on both sides, bots from the Ukrainian side contributed a louder voice while bots on the Russian side demonstrated more effective communication. In addition, there were differences and similarities between bots and non-bots in the behavior of online conversations, but the difference seemed to be relatively weaker than those found in previous studies.

An Improvised Sentiment Analysis Model on Twitter Data Using Stochastic Gradient Descent (SGD) Optimization Algorithm in Stochastic Gate Neural Network (SGNN).

Sentiment analysis is one of the effective techniques for mining the opinion from shapeless data contains text like review of the products, review of the movie. Sentiment analysis is used as a key to gather response from consumers, reviews of brands, marketing analyses, and political campaigns. In the subject of natural processing, performing sentiment analysis using the data obtained from Twitter is considered as a new study in these days. The dataset is gathered using the Twitter API and the Twitter package. The analysis of Twitter data is a process which takes place automatically by text data analysis to determine the view of public on the specified topic. Here, an improvised sentimental analysis model is proposed to identify the polarity of the tweets such as positive, neutral and negative. In this paper, stochastic gradient descent (SGD) algorithm uses stochastic gradient neural network (SGNN) to categorize the sentiment analysis on basis of tweets provided by the Twitter users and the proposed stochastic gradient descent optimization Algorithm based on stochastic gradient neural network (SGDOA-SGNN) provides better performance when compared with the existing Forest-Whale Optimization Algorithm based on deep neural network F-WOA-DNN model.

Debating stereotypes: Online reactions to the vice-presidential debate of 2020.

The 2020 Vice-Presidential debate afforded the opportunity to examine online reactions toward a woman of color, Kamala Harris, and a white man, Mike Pence, as they vied for the same position. We collected tweets from the Twitter API related to Harris and Pence, mainly using neutral hashtags. We examined keywords for gender and race slurs and conducted a multivariate analysis of tweet sentiment. Gender and racial slurs surface in both Harris and Pence datasets, showcasing the insidious nature of sexist and racist stereotypes that seep into online conversations regarding a high-status job debate. As anticipated, tweets regarding Harris contained a higher proportion of racist and sexist curse words, highlighting greater levels of harassment and "intersectional," multi-ethnic/gender attacks. Racial insults targeting Blacks or Asians were more negative than those associated with Whites. Unexpectedly, tweets related to Harris were more positive in average sentiment than those regarding Pence. Yet, there were significantly more retweets, and more negativity of retweets, relating to Harris than to Pence, underscoring the relatively widespread broadcasting of derogatory messages about Harris. Overall, we found that harassing messages toward the candidates reinforced traditional race and gender stereotypes and bolstered the status of those who posted negative content by attaining more retweets. Harassers routinely invoked well-worn, stereotypical insults in their attacks, especially when targeting a multiracial woman.

Rancang Bangun Engine Sentimen Analisis Tingkat Popularitas Kopi Berdasarkan Pengolahannya Menggunakan Teknologi Big Data

Demand for coffee products continues to increase along with population growth. The demand for a product is seen from the public's perception of the product. Community perceptions can be found through tweets on social media Twitter. This perception can be used to analyze sentiment towards a product. This approach is called Sentiment Analysis and to analyze it requires Big Data Technology. This study aims to design a Sentiment Engine Analysis of the Level of Popularity of Coffee Based on Processing Using Big Data Technology to find out the sentiments of people around the world towards processed coffee drinks through Twitter social media. This study uses the process of collecting tweet data from Twitter using the Twitter API, data processing, classification into positive, negative, and neutral sentiments using the Naïve Bayes method, as well as data visualization in graphical form. The data generated in this study amounted to 1,253,971 data in 1 year with 1800 training data and 450 test data. The evaluation results with the Naïve Bayes classification are 92.67% accuracy, 98.52% precision, 88.67% recall, and 93.33% f-measure.