Twitter Data Research Articles

Stream ETL framework for twitter-based sentiment analysis: Leveraging big data technologies

Twitter has emerged as a rich source of real-time data, providing valuable insights across various domains such as healthcare and business. Sentiment analysis is crucial in understanding public reactions and sentiments expressed on Twitter, empowering organizations to make informed decisions. However, efficiently analyzing sentiment from social media data, presents a challenge for real-time streaming. Conventional Extract-Transform-Load (ETL) methods, inadequate for this challenge, limit their applicability in processing vast volumes of Twitter data. Big data technologies like Kafka, Spark, Hadoop HDFS, Hive, and HBase have become indispensable in addressing this challenge. To address this, we propose a stream ETL framework for Twitter-based sentiment analysis, leveraging Kafka, Spark, Cassandra, HBase, Hive, and HDFS. Our framework enables data stream processing, bias detection and correction, sentiment-based analysis, and visualization of tweets’ geospatial distribution. We present a set of use case studies to illustrate the applicability of the proposed framework comprises of sentiment classification, and bias detection and correction capability. We also present a comparative study to demonstrate the performance of data streaming processing, analysis, and visualization that has been implemented using multiple big data technologies under different parameter settings. Experimental results demonstrate the framework scalability and trade-off factors of the data stream processing pipeline in the execution of big data processing tasks.

Ontology-Based Data Collection for a Hybrid Outbreak Detection Method Using Social Media.

Given the persistent global challenge presented by rapidly spreading diseases, as evidenced notably by the widespread impact of the COVID-19 pandemic on both human health and economies worldwide, the necessity of developing effective infectious disease prediction models has become of utmost importance. In this context, the utilization of online social media platforms as valuable tools in healthcare settings has gained prominence, offering direct avenues for disseminating critical health information to the public in a timely and accessible manner. Propelled by the ubiquitous accessibility of the internet through computers and mobile devices, these platforms promise to revolutionize traditional detection methods, providing more immediate and reliable epidemiological insights. Leveraging this paradigm shift, our proposed framework harnesses Twitter data associated with infectious disease symptoms, employing ontology to identify and curate relevant tweets. Central to our methodology is a hybrid model that integrates XGBoost and Bidirectional Long Short-Term Memory (BiLSTM) architectures. The integration of XGBoost addresses the challenge of handling small dataset sizes, inherent during outbreaks due to limited time series data. XGBoost serves as a cornerstone for minimizing the loss function and identifying optimal features from our multivariate time series data. Subsequently, the combined dataset, comprising original features and predicted values by XGBoost, is channeled into the BiLSTM for further processing. Through extensive experimentation with a dataset spanning multiple infectious disease outbreaks, our hybrid model demonstrates superior predictive performance compared to state-of-the-art and baseline models. By enhancing forecasting accuracy and outbreak tracking capabilities, our model offers promising prospects for assisting health authorities in mitigating fatalities and proactively preparing for potential outbreaks.

Fluctuations and extreme events in the public attention on Italian legislative elections

The share of social media attention to political candidates was shown to be a good predictor of election outcomes in several studies. This attention to individual candidates fluctuates due to incoming daily news and sometimes reflects long-term trends. By analyzing Twitter data in the 2013 and 2022 election campaign we observe that, on short timescales, the dynamics can be effectively characterized by a mean-reverting diffusion process on a logarithmic scale. This implies that the response to news and the exchange of opinions on Twitter lead to attention fluctuations spanning orders of magnitudes. However, these fluctuations remain centered around certain average levels of popularity, which change slowly in contrast to the rapid daily and hourly variations driven by Twitter trends and news. In particular, on our 2013 data we are able to estimate the dominant timescale of fluctuations at around three hours. Finally, by considering the extreme data points in the tail of the attention variation distribution, we could identify critical events in the electoral campaign period and extract useful information from the flow of data.

Analysis Of The Use Of Nazief-Adriani Stemming And Porter Stemming In Covid-19 Twitter Sentiment Analysis With Term Frequency-Inverse Document Frequency Weighting Based On K-Nearest Neighbor Algorithm

Abstract. This system was developed to determine the accuracy of sentiment analysis on Twitter regarding the COVID-19 issue using the Nazief-Adriani and Porter stemmers with TF-IDF weighting, along with a classification process using K-Nearest Neighbor (KNN) that resulted in a comparison of 48.24% for Nazief-Adriani and 48.24% for Porter. Purpose: This research aims to determine the accuracy of the Nazief-Adriani and Porter stemmer algorithms in performing text preprocessing using a dataset from Indonesian-language Twitter. This research involves word weighting using TF-IDF and classification using the K-Nearest Neighbor (KNN) algorithm. Methods/Study design/approach: The experimentation was conducted by applying the Nazief-Adriani and Porter stemmer algorithm methods, utilizing data sourced from Twitter related to COVID-19. Subsequently, the data underwent text preprocessing, stemming, TF-IDF weighting, accuracy testing of training and testing data using K-Nearest Neighbor (KNN) algorithm, and the accuracy of both stemmers was calculated employing a confusion matrix table. Result/Findings: This study obtained reasonably accurate results in testing the Nazief-Adriani stemmer with an accuracy of 50.98%, applied to sentiment analysis of COVID-19-related Twitter data using the Indonesian language. As for the accuracy of the Porter stemmer, it achieved an accuracy rate of 48.24%. Novelty/Originality/Value: Feature selection is crucial in stemmer accuracy testing. Therefore, in this study, feature selection is carried out using the Nazief-Adriani and Porter stemmers for testing purposes, and the accuracy data classification is conducted using the K-Nearest Neighbor (KNN) algorithm

Sentiment Analysis on Twitter Social Media Regarding Covid-19 Vaccination with Naive Bayes Classifier (NBC) and Bidirectional Encoder Representations from Transformers (BERT)

Abstract. The Covid-19 vaccine is an important tool to stop the Covid-19 pandemic, however, there are pros and cons from the public regarding this Covid-19 vaccine. Purpose: These responses were conveyed by the public in many ways, one of which is through social media such as Twitter. Responses given by the public regarding the Covid-19 vaccination can be analyzed and categorized into responses with positive, neutral or negative sentiments. Methods: In this study, sentiment analysis was carried out regarding Covid-19 vaccination originating from Twitter using the Naïve Bayes Classifier (NBC) and Bidirectional Encoder Representations from Transformers (BERT) algorithms. The data used in this study is public tweet data regarding the Covid-19 vaccination with a total of 29,447 tweet data in English. Result: Sentiment analysis begins with data preprocessing on the dataset used for data normalization and data cleaning before classification. Then word vectorization was performed with TF-IDF and data classification was performed using the Naïve Bayes Classifier (NBC) and Bidirectional Encoder Representations from Transformers (BERT) algorithms. From the classification results, an accuracy value of 73% was obtained for the Naïve Bayes Classifier (NBC) algorithm and 83% for the Bidirectional Encoder Representations from Transformers (BERT) algorithm. Novelty: A direct comparison between classical models such as NBC and modern deep learning models such as BERT offers new insights into the advantages and disadvantages of both approaches in processing Twitter data. Additionally, this study proposes temporal sentiment analysis, which allows evaluating changes in public sentiment regarding vaccination over time. Another innovation is the implementation of a hybrid approach to data cleansing that combines traditional methods with the natural language processing capabilities of BERT, which more effectively addresses typical Twitter data issues such as slang and spelling errors. Finally, this research also expands sentiment classification to be multi-label, identifying more specific sentiment categories such as trust, fear, or doubt, which provides a deeper understanding of public opinion.

A Comparative Analysis of MultinomialNB, SVM, and BERT on Garuda Indonesia Twitter Sentiment

This study investigates customer sentiment towards Garuda Indonesia Airlines (GIA) using sentiment analysis of Twitter data. The research aims to identify prevailing sentiments, uncover common themes in customer feedback, and provide recommendations for improving customer satisfaction and brand loyalty. A dataset of 1,250 tweets from March 2007 to July 2024 was collected and pre-processed, including cleaning, language detection, and tokenization. Sentiment analysis was conducted using three models: MultinomialNB, SVM, and BERT.The results indicate that BERT outperformed both MultinomialNB and SVM in sentiment classification accuracy, achieving 75.6%. This highlights the effectiveness of BERT in capturing contextual meaning within customer reviews. The findings of this research will contribute to a deeper understanding of customer sentiment towards GIA and inform strategies for enhancing customer experience and brand image.

P-TIMA: a framework of T witter threat intelligence mining and analysis based on a prompt-learning NER model

Abstract Open-source information platforms such as Twitter continuously provide the latest threat intelligence, including new vulnerabilities and in-the-wild exploitations of advanced persistent threat (APT) groups. Automated extraction of threat intelligence from Twitter has become crucial for defenders to access up-to-date threat knowledge. However, existing studies mainly rely on supervised learning methods to extract threat intelligence knowledge, such as entities, which require a large amount of annotated data. This paper presents Threat Intelligence Mining and Analysis based on Prompt Learning (P-TIMA), a framework specifically crafted for extracting and analyzing threat intelligence from Twitter. P-TIMA employs our innovative few-shot entity recognition method, SecEntPrompt (SEP), built on prompt learning, to extract vulnerability intelligence from Twitter. Additionally, P-TIMA analyzes and profiles the overarching vulnerability intelligence obtained from Twitter, along with in-the-wild exploitation intelligence of APT groups. The SEP improves the average entity recognition F1 score by 3.62-4.40 compared with the best-performing comparison model and outperforms the method based on the large language model on recognition performance and inference time. To validate our framework, we apply P-TIMA to extract vulnerability-related threat intelligence from real Twitter data. Through case studies, we then analyze trends in vulnerability threats and the exploitation capabilities of APT groups. In conclusion, our framework provides a more efficient and accurate method for extracting threat intelligence from Twitter, enabling defenders to stay up-to-date with the latest threat trends and helping them improve their defense strategies against cyber attacks.

An Evaluation of the Maternal Patient Experience through Natural Language Processing Techniques: The Case of Twitter Data in the United States during COVID-19

The healthcare sector constantly investigates ways to improve patient outcomes and provide more patient-centered care. Delivering quality medical care involves ensuring that patients have a positive experience. Most healthcare organizations use patient survey feedback to measure patients’ experiences. However, the power of social media can be harnessed using artificial intelligence and machine learning techniques to provide researchers with valuable insights into understanding patient experience and care. Our primary research objective is to develop a social media analytics model to evaluate the maternal patient experience during the COVID-19 pandemic. We used the “COVID-19 Tweets” Dataset, which has over 28 million tweets, and extracted tweets from the US with words relevant to maternal patients. The maternal patient cohort was selected because the United States has the highest percentage of maternal mortality and morbidity rate among the developed countries in the world. We evaluated patient experience using natural language processing (NLP) techniques such as word clouds, word clustering, frequency analysis, and network analysis of words that relate to “pains” and “gains” regarding the maternal patient experience, which are expressed through social media. The pandemic showcased the worries of mothers and providers on the risks of COVID-19. However, many people also shared how they survived the pandemic. Both providers and maternal patients had concerns regarding the pregnancy risks due to COVID-19. This model will help process improvement experts without domain expertise to understand the various domain challenges efficiently. Such insights can help decision-makers improve the patient care system.

Sentiment Analysis of Indonesia 2024 Election with a Comparison of Naive Bayes and KNN Algorithms on Twitter

In the 2024 General Election, the Recapitulation Information System (SIREKAP) was used to capture the vote count results electronically. However, the use of SIREKAP raises various opinions in the community, both positive and negative, regarding the accuracy of the uploaded data. This study aims to analyze public sentiment towards the use of SIREKAP in the 2024 Election through Twitter data, using the Naive Bayes and KNN algorithms. The results showed that the Naive Bayes algorithm was superior with an accuracy of 93.37%, while KNN achieved an accuracy of 77.92%. The novelty of this research is to conduct sentiment analysis and provide insight into how people perceive the use of SIREKAP in the 2024 Election through Twitter data.

Public Perception of the Tobacco 21 Amendment on Twitter in the United States: Observational Study.

Following the signing of the Tobacco 21 Amendment (T21) in December 2019 to raise the minimum legal age for the sale of tobacco products from 18 to 21 years in the United States, there is a need to monitor public responses and potential unintended consequences. Social media platforms, such as Twitter (subsequently rebranded as X), can provide rich data on public perceptions. This study contributes to the literature using Twitter data to assess the knowledge and beliefs of T21. Twitter data were collected from November 2019 to February 2021 using the Twitter streaming application programming interface with keywords related to vaping or e-cigarettes, such as "vape," "ecig," etc. The temporal trend of the T21 discussion on Twitter was examined using the mean number of daily T21-related tweets. Inductive methods were used to manually code the tweets into different sentiment groups (positive, neutral, and negative) based on the attitude expressed toward the policy by 3 coders with high interrater reliability. Topics discussed were examined within each sentiment group through theme analyses. Among the collected 3197 tweets, 2169 tweets were related to T21, of which 444 tweets (20.5%) showed a positive attitude, 736 (33.9%) showed a negative attitude, and 989 (45.6%) showed a neutral attitude. The temporal trend showed a clear peak in the number of tweets around January 2020, following the enactment of this legislation. For positive tweets, the most frequent topics were "avoidance of further regulation" (120/444, 27%), "Enforce T21" (110/444, 24.8%), and "health benefits" (81/444, 18.2%). For negative tweets, the most frequent topics were "general disagreement or frustration" (207/736, 28.1%) and "will still use tobacco" (188/736, 25.5%). Neutral tweets were primarily "public service announcements (PSA) or news posts" (782/989, 79.1%). Overall, we find that one-third of tweets displayed a negative attitude toward T21 during the study period. Many were frustrated with T21 and reported that underage consumers could still obtain products. Social media data provide a timely opportunity to monitor public perceptions and responses to regulatory actions. Continued monitoring can inform enforcement efforts and potential unintended consequences of T21.

Georeferenced X (formerly twitter) data as a proxy of mobility behaviour: case study of Norway

Georeferenced messages on social media represent a powerful data source to gain a different perspective for estimating mobility behaviour, which is still mainly based on travel surveys. These data are openly available, yet few studies have explored their potential. This paper assesses the feasibility of large-scale Twitter data as a proxy of human mobility behaviour to complement traditional travel surveys, and for calibration and validation of transport models. Almost 12 million Tweets from more than 90,000 users were further analysed to detect the trip patterns at municipality level in Norway from 2012 to 2022. Results showed that the mobility patterns changed between 2014 and 2019 for the travel survey, as for 2019 most of the reported trips were short and concentrated in the densely populated areas of the country, where most respondents lived, triggering a lack of information for certain areas. In contrast, Twitter data presented a more stable data source along both years with similar population distribution and average trip length. Although Twitter data have limitations in relation to the socio-demographic information of the users, it could complement the travel survey given the broader spatial and temporal distribution of this large-scale data.

Measuring receptivity to misinformation at scale on a social media platform.

Measuring the impact of online misinformation is challenging. Traditional measures, such as user views or shares on social media, are incomplete because not everyone who is exposed to misinformation is equally likely to believe it. To address this issue, we developed a method that combines survey data with observational Twitter data to probabilistically estimate the number of users both exposed to and likely to believe a specific news story. As a proof of concept, we applied this method to 139 viral news articles and find that although false news reaches an audience with diverse political views, users who are both exposed and receptive to believing false news tend to have more extreme ideologies. These receptive users are also more likely to encounter misinformation earlier than those who are unlikely to believe it. This mismatch between overall user exposure and receptive user exposure underscores the limitation of relying solely on exposure or interaction data to measure the impact of misinformation, as well as the challenge of implementing effective interventions. To demonstrate how our approach can address this challenge, we then conducted data-driven simulations of common interventions used by social media platforms. We find that these interventions are only modestly effective at reducing exposure among users likely to believe misinformation, and their effectiveness quickly diminishes unless implemented soon after misinformation's initial spread. Our paper provides a more precise estimate of misinformation's impact by focusing on the exposure of users likely to believe it, offering insights for effective mitigation strategies on social media.

From Tweets to Streets: Observational Study on the Association Between Twitter Sentiment and Anti-Asian Hate Crimes in New York City from 2019 to 2022.

Anti-Asian hate crimes escalated during the COVID-19 pandemic; however, limited research has explored the association between social media sentiment and hate crimes toward Asian communities. This study aims to investigate the relationship between Twitter (rebranded as X) sentiment data and the occurrence of anti-Asian hate crimes in New York City from 2019 to 2022, a period encompassing both before and during COVID-19 pandemic conditions. We used a hate crime dataset from the New York City Police Department. This dataset included detailed information on the occurrence of anti-Asian hate crimes at the police precinct level from 2019 to 2022. We used Twitter's application programming interface for Academic Research to collect a random 1% sample of publicly available Twitter data in New York State, including New York City, that included 1 or more of the selected Asian-related keywords and applied support vector machine to classify sentiment. We measured sentiment toward the Asian community using the rates of negative and positive sentiment expressed in tweets at the monthly level (N=48). We used negative binomial models to explore the associations between sentiment levels and the number of anti-Asian hate crimes in the same month. We further adjusted our models for confounders such as the unemployment rate and the emergence of the COVID-19 pandemic. As sensitivity analyses, we used distributed lag models to capture 1- to 2-month lag times. A point increase of 1% in negative sentiment rate toward the Asian community in the same month was associated with a 24% increase (incidence rate ratio [IRR] 1.24; 95% CI 1.07-1.44; P=.005) in the number of anti-Asian hate crimes. The association was slightly attenuated after adjusting for unemployment and COVID-19 emergence (ie, after March 2020; P=.008). The positive sentiment toward Asian tweets with a 0-month lag was associated with a 12% decrease (IRR 0.88; 95% CI 0.79-0.97; P=.002) in expected anti-Asian hate crimes in the same month, but the relationship was no longer significant after adjusting for the unemployment rate and the emergence of COVID-19 pandemic (P=.11). A higher negative sentiment level was associated with more hate crimes specifically targeting the Asian community in the same month. The findings highlight the importance of monitoring public sentiment to predict and potentially mitigate hate crimes against Asian individuals.

Herding and investor sentiment after the cryptocurrency crash: evidence from Twitter and natural language processing

Although the 2022 cryptocurrency market crash prompted despair among investors, the rallying cry, “wagmi” (We’re all gonna make it.) emerged among cryptocurrency enthusiasts in the aftermath. Did cryptocurrency enthusiasts respond to this crash differently compared to traditional investors? Using natural language processing techniques applied to Twitter data, this study employed a difference-in-differences method to determine whether the cryptocurrency market crash had a differential effect on investor sentiment toward cryptocurrency enthusiasts relative to more traditional investors. The results indicate that the crash affected investor sentiment among cryptocurrency enthusiastic investors differently from traditional investors. In particular, cryptocurrency enthusiasts’ tweets became more neutral and, surprisingly, less negative. This result appears to be primarily driven by a deliberate, collectivist effort to promote positivity within the cryptocurrency community (“wagmi”). Considering the more nuanced emotional content of tweets, it appears that cryptocurrency enthusiasts expressed less joy and surprise in the aftermath of the cryptocurrency crash than traditional investors. Moreover, cryptocurrency enthusiasts tweeted more frequently after the cryptocurrency crash, with a relative increase in tweet frequency of approximately one tweet per day. An analysis of the specific textual content of tweets provides evidence of herding behavior among cryptocurrency enthusiasts.

Predicting Cardiovascular Disease Risk Using Web-Text Sentiment Analysis and Hybrid Deep Learning Models

Background: Sentiment Analysis (SA) has emerged as a key tool within Natural Language Processing (NLP) for quantifying emotions expressed in Web Text (WT). Its application in healthcare, particularly in predicting cardiovascular diseases (CD), shows promise. Sentiments related to stress, anger, or other emotional states have been linked to increased CD risk, making Web-Text Sentiment Analysis (WT-SA) a valuable tool in public health prediction. This study compares WT-SA to demographic data from the Centers for Disease Control and Prevention (CDC) in predicting CD risks. Methods: Twitter data was analyzed using SA techniques to assess sentiments related to CD. A hybrid deep learning (DL) model combining 3D-Convolutional Neural Networks (3D-CNN) and Recurrent Neural Networks (RNN) was utilized alongside traditional machine learning (ML) models: Naïve Bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR), and CatBoost. The WT data, spanning three years (2020-2023), was split into training (75%) and testing (25%) datasets. Model performance was evaluated using Accuracy, Precision, Recall, and F1 score. Results: The hybrid 3D-CNN+RNN model achieved the highest test accuracy of 0.95 on Twitter data, outperforming all other models. SVM, LR, NB, and CatBoost achieved accuracies of 0.89, 0.88, 0.75, and 0.77, respectively. When applied to the CDC dataset, the hybrid model reached an accuracy of 0.678, still outperforming the other models. Overall, the WT-SA model demonstrated superior performance compared to using demographic data alone. Conclusion: WT-SA, when combined with hybrid DL models, is a more effective method for predicting CD risk than demographic-based models. This study determined the potential of NLP and DL techniques in leveraging social media data for public health monitoring, suggesting that WT-SA could be a valuable tool for predicting CD risks and enhancing early intervention efforts.

Virality classification from Twitter data using pre-trained language model and multi-layer perceptron

Twitter is one of the well-known text-based social media that is often used to disseminate content. According to Katadata, Indonesia ranked fifth in the world in 2023. So many people or organizations want to make tweets go viral. Therefore, this research aims to develop a model that uses tweet data from the Indonesian language Twitter social media to categorize the level of virality. There are several tasks in classifying the level of virality, such as upsampling data, predicting sentiment and emotion, and text embedding. Upsampling data was carried out because the dataset used was an imbalanced dataset. Data upsampling, emotions, and text embedding is carried out using the bidirectional encoder representation from transformers (BERT) model. Meanwhile, sentiment prediction uses the Ro-bustly optimized BERT pretraining approach (RoBERTa). The results of text embedding, sentiment, emotion, will be combined with Twitter metadata then all features will be fed into the multi-layer perceptron (MLP) model to classifying the level of virality which is divided into 3 classes based on the number of retweets, namely low, medium and high. The proposed method produces an F1-score of 49% and an accuracy of 95% and performs better than the baseline model.

Learning Joint Topic Representation for Detecting Drift in Social Media Text

Social media texts like tweets and blogs are collaboratively created by human interaction. Rapidly changing trends are leading to topic drift in the social media text. This drift is usually associated with words and hashtags. However, geotags play an essential part in determining topic distribution with location context. The rate of change in the distribution of words, hashtags and geotags cannot be considered uniform and must be handled accordingly. This paper builds a topic model that associates the topic with a mixture of distributions of words, hashtags and geotags. Stochastic gradient Langevin dynamic model with varying mini-batch sizes is used to capture the changes due to the asynchronous distribution of words and tags. Topic representations with co-occurrence and location contexts are specified as hashtag context vector and geotag context vector respectively. These two vectors are jointly learned to yield topical word embedding vectors over time conditioned on hashtags and geotags that can predict location-based topical variations effectively. When evaluated with Chennai and UK geolocated Twitter data, the proposed joint topical word embedding model enhanced by the social tags context, outperforms other methods.

Performance of Deep Feed-Forward Neural Network Algorithm Based on Content-Based Filtering Approach

Background: Selecting a restaurant in a diverse city like Bandung can be challenging. This study leverages Twitter data and local restaurant information to develop an advanced recommendation system to improve decision-making. Objective: The system integrates content-based filtering (CBF) with deep feedforward neural network (DFF) classification to enhance the accuracy and relevance of restaurant recommendations. Methods: Data was sourced from Twitter and PergiKuliner, with restaurant-related tweets converted into rating values. The CBF combined Bag of Words (BoW) and cosine similarity, followed by DFF classification. SMOTE was applied during training to address data imbalance. Results: The initial evaluation of CBF showed a Mean Absolute Error (MAE) of 0.0614 and a Root Mean Square Error (RMSE) of 0.0934. The optimal DFF configuration in the first phase used two layers with 32/16 nodes, a dropout rate of 0.3, and a 20% test size. This setup achieved an accuracy of 81.08%, precision of 82.89%, recall of 76.93%, and f1-scores of 79.23%. In the second phase, the RMSprop optimizer improved accuracy to 81.30%, and tuning the learning rate to 0.0596 further increased accuracy to 89%, marking a 9.77% improvement. Conclusion: The research successfully developed a robust recommendation system, significantly improving restaurant recommendation accuracy in Bandung. The 9.77% accuracy increase highlights the importance of hyperparameter tuning. SMOTE also proved crucial in balancing the dataset, contributing to a well-rounded learning model. Future studies could explore additional contextual factors and experiment with recurrent or convolutional neural networks to enhance performance further.

Sentiment Analysis of Sirekap Tweets Using CNN Algorithm

Background: The research investigates the application of deep learning models for sentiment analysis on Twitter data related to Indonesia's Sirekap system. Sentiment analysis is crucial for understanding public opinion and enhancing the transparency and reliability of election result recapitulation processes. Objective: The objective of this study is to compare the performance of Convolutional Neural Networks (CNN) and CNN-LSTM models in analyzing sentiments from tweets about the Sirekap system. The study aims to identify the most effective model and preprocessing techniques to improve sentiment classification accuracy. Methods: A comprehensive data preprocessing pipeline was implemented, including cleansing, case folding, tokenizing, normalization, stopword removal, and stemming. To address class imbalance, the SMOTE technique was applied. The models were trained and evaluated using accuracy, precision, recall, and F1-score metrics. Pre-trained word embeddings were used to enhance model performance. Results: The CNN model achieved an accuracy of 85.90%, outperforming the CNN-LSTM model, which achieved 79.91% accuracy. Additionally, the CNN model demonstrated superior precision, recall, and F1-score metrics compared to the CNN-LSTM model. The thorough preprocessing and handling of class imbalance significantly contributed to the enhanced performance of the CNN model. Conclusion: The research emphasizes the effectiveness of deep learning approaches, particularly CNNs, in sentiment analysis tasks. The findings highlight the importance of comprehensive preprocessing and class imbalance handling. The use of pre-trained word embeddings and various evaluation metrics ensures robust model performance. These insights contribute to improving the accuracy and efficiency of sentiment classification, thereby enhancing the reliability and transparency of election result recapitulation processes.

Early morning hour and evening usage habits increase misinformation-spread

Social media manipulation poses a significant threat to cognitive autonomy and unbiased opinion formation. Prior literature explored the relationship between online activity and emotional state, cognitive resources, sunlight and weather. However, a limited understanding exists regarding the role of time of day in content spread and the impact of user activity patterns on susceptibility to mis- and disinformation. This work uncovers a strong correlation between user activity time patterns and the tendency to spread potentially disinformative content. Through quantitative analysis of Twitter (now X) data, we examine how user activity throughout the day aligns with diurnal behavioural archetypes. Evening types exhibit a significantly higher inclination towards spreading potentially disinformative content, which is more likely at night-time. This knowledge can become crucial for developing targeted interventions and strategies that mitigate misinformation spread by addressing vulnerable periods and user groups more susceptible to manipulation.