Social Media Text Research Articles

LEVERAGING CORPUS LINGUISTICS AND DATA-DRIVEN DEEP LEARNING FOR TEXTUAL EMOTION ANALYSIS

Emotions have played a major part in the conversation, as they express context to the conversation. Text or words in conversation contain contextual and lexical meanings. In recent times, obtaining emotion from the text has been an attractive area of research. With the emergence of machine learning (ML) algorithms and hardware to aid the ML method, identifying emotion from the text with ML provides significant and promising solutions. The main objective of Textual Emotion Analysis (TEA) is to analyze and extract the user’s emotional states in the text. Many different Complex Systems and Deep Learning (DL) algorithms have been fast-paced developed and proved their effectiveness in several fields including audio, image, and natural language processing (NLP). This has moved researchers away from the classical ML to DL for their academic research work. This study develops a new Corpus Linguistics and Data-Driven Deep Learning for Textual Emotion Analysis (CLD3L-TEA) technique. The CLD3L-TEA technique mainly investigates the distinct types of emotions that endure in the social media text. In the CLD3L-TEA model, the raw data can be pre-processed in distinct ways. Next, a multi-weighted TF–IDF model is used to generate feature vectors. For the identification of emotions, the CLD3L-TEA technique applied a gated recurrent unit (GRU). At last, the hyperparameter range of the GRU model is executed by the Fractal Harris Hawks Optimization (HHO) model. The experimental validation of the CLD3L-TEA technique on a benchmark dataset illustrates the supremacy of this technique over recent approaches.

Exploring tourist perceptions of calligraphic landscapes: Insights from social media text analysis

Calligraphic landscapes, as distinctive cultural symbols and landscapes with Chinese characteristics, are widely used in urban design, placemaking, and tourism promotion. In cultural heritage tourism, tourists’ perceptions of the symbolic meanings of landscapes significantly influence their travel experiences. This study primarily utilizes social media text analysis to explore the perceptual characteristics and symbolic meanings of calligraphic landscapes in different touristic contexts. Using Python tools, user-generated content was extracted from the Xiaohongshu app and analyzed with ROST CM6, VOSviewer, and NVivo 20 to conduct systematic quantitative and qualitative analyses, including content analysis, semantic network analysis, and co-occurrence clustering. The findings indicate that cultural exchanges on social media significantly enhance public perception of the symbolic meanings of touristic spaces. As online check-in behavior becomes increasingly popular, calligraphic landscapes have gained new esthetic-symbolic meanings among young tourists, becoming part of fashion culture and reflecting the digitalization of a sense of place. In addition, user-generated content reveals that tourists’ perceptions of calligraphic landscapes are intricately linked to place recognition, cultural symbolism, calligraphic appreciation, heritage value, and esthetic experiences. As a significant cultural symbol, calligraphic landscapes are frequently encountered during travel, with their symbolic meanings varying according to the surrounding environment, thereby influencing tourists’ preferences in diverse settings. Furthermore, this study proposes several innovative strategies for designing calligraphic landscapes. This research not only validates the feasibility of web text analysis for exploring the symbolic meanings of cultural landscapes but also enhances theoretical perspectives on how symbolic landscapes shape tourists’ psychological and behavioral responses.

Hierarchical Attention and Contextual Embedding for Robust Sarcasm Detection

Objective: The study aims to develop a technique for sarcasm detection in social media text to enrich the sentiment analysis. Methods: The methodology used in the present research is as follows: emotion-embedded vectors for capturing the emotional content of the text, dynamic contextual modulation for the adaption of the model to the given context, and Hierarchical attention mechanism for segmentation of the text at the different level of abstraction. Findings: Evaluation with the test set proved that the proposed model achieved accuracy rates 89% higher than the benchmark models. Including these several complicated methods helped achieve greater accuracy and F1 measures, contributing to sarcasm detection efficiency. Novelty: This approach ensures that vital sarcastic alerts are detected, providing a better text analysis and increasing sentiment analysis's accuracy and robustness. Keywords: Sarcasm detection, Sentiment analysis, Natural language processing, Deep learning, Opinion mining

Leveraging Unsupervised Task Adaptation and Semi‐Supervised Learning With Semantic‐Enriched Representations for Online Sexism Detection

ABSTRACTOver the past decade, the proliferation of hateful and sexist content targeting women on social media has become a concerning issue, adversely affecting women's lives and freedom of expression. Previous efforts to detect online sexism have utilized monolingual ensemble transformers combined with data augmentation techniques that incorporate related‐domain data, such as hate speech. However, these approaches often struggle to capture the full diversity and complexity of sexism due to limitations in the size and quality of training data. In this study, we introduce a novel sexism detection system that employs in‐domain unlabeled data through unsupervised task‐adaptation techniques and semi‐supervised learning, using an efficient single multilingual transformer model. Additionally, we incorporate a Sentence‐BERT layer to enhance our system with semantically meaningful sentence embeddings. Our proposed system outperforms existing state‐of‐the‐art methods across all tasks and datasets, demonstrating its effectiveness in detecting and addressing sexism in social media text. These results underscore the potential of our approach, providing a foundation for further research and practical applications.

Deceptively simple: An outsider's perspective on natural language processing

AbstractThis article highlights a collection of ideas with an underlying deceptive simplicity that addresses several practical challenges in computational social science and generative AI safety. These ideas lead to (1) an interpretable and quantifiable framework for political polarization; (2) a language identifier robust to noisy social media text settings; (3) a cross‐lingual semantic sampler that harnesses code‐switching; and (4) a bias audit framework that uncovers shocking racism, antisemitism, misogyny, and other biases in a wide suite of large language models.

Advanced Comparative Analysis of Machine Learning and Transformer Models for Depression and Suicide Detection in Social Media Texts

Advanced Comparative Analysis of Machine Learning and Transformer Models for Depression and Suicide Detection in Social Media Texts

A Comparative Study of Transformer-based Models for Hate-Speech Detection in English-Kiswahili Code-Switched Social Media Text

The transformer architecture, first introduced in 2017 by researchers at Google, has revolutionized natural language processing in various tasks, including text classification. This architecture formed the basis of future models such as those used in hate speech detection in code-switched text. In this research, we conduct a comparative study of transformer-based models for hate speech detection in English-Kiswahili code-switched text. First, the models were compared as feature extractors using a traditional classifier and then as end-to-end classifiers. The three multilingual transformer-based models compared include mBERT, mDistilBERT and XLM-RoBERTa, using SVM as the traditional classifier for the extracted features. The HateSpeech_Kenya dataset, sourced from Kaggle, was utilized in this study. As a feature extractor, mBERT’s hidden states trained the highest-performing SVM with an accuracy of 0.5461 and a macro f1 score of 0.40. Among the three models evaluated, XLM-RoBERTa achieved the highest accuracy of 0.6069 and a macro f1 score of 0.49 on a balanced dataset. In contrast, mBERT achieved the highest accuracy of 0.7820 and a macro f1 score of 0.53 on an imbalanced dataset. The comparative study establishes that using transformer-based models as end-to-end classifiers generally performs better than using them as feature extractors with traditional classifiers. This is because directly training the models allows them to learn more task-specific features. Furthermore, the varying performance across balanced and imbalanced datasets highlights the need for careful model selection based on the dataset characteristics and specific task requirements.

Sentiment Classification of Anxiety-Related Texts in Social Media via Fuzing Linguistic and Semantic Features

Sentiment Classification of Anxiety-Related Texts in Social Media via Fuzing Linguistic and Semantic Features

Comparative analysis of machine learning algorithms for sentiment classification in social media text

In the era of social media, sentiment analysis has become crucial for understanding public opinion. This study presents a comparative analysis of five machine learning algorithms for sentiment classification in social media text: Logistic Regression, Support Vector Machines (SVM), Random Forest, Naive Bayes, and Gradient Boosting. Using a dataset of 100,000 tweets collected over three months, we evaluated these algorithm's performance in classifying sentiments as positive, negative, or neutral. The data underwent extensive preprocessing, including cleaning, normalization, and addressing class imbalance using SMOTE. Our results show that Logistic Regression and SVM achieved the highest overall accuracy at 86.22%, demonstrating balanced performance across all sentiment classes. Random Forest followed closely with 82.59% accuracy, while Naive Bayes and Gradient Boosting showed lower but still noteworthy performance at 70.45% and 69.96% respectively. All models exhibited challenges in classifying negative sentiments, suggesting potential areas for improvement. The study provides insights into each algorithm's strengths and weaknesses, offering guidance for practitioners in selecting appropriate methods for sentiment analysis tasks. Our findings contribute to the ongoing research in applying machine learning to the complex task of sentiment analysis in the rapidly evolving landscape of social media communication.

Evaluation of emotion classification schemes in social media text: an annotation-based approach

BackgroundEmotion analysis of social media texts is an innovative method for gaining insight into the mental state of the public and understanding social phenomena. However, emotion is a complex psychological phenomenon, and there are various emotion classification schemes. Which one is suitable for textual emotion analysis?MethodsWe proposed a framework for evaluating emotion classification schemes based on manual annotation experiments. Considering both the quality and efficiency of emotion analysis, we identified five criteria, which are solidity, coverage, agreement, compactness, and distinction. Qualitative and quantitative factors were synthesized using the AHP, where quantitative metrics were derived from annotation experiments. Applying this framework, 2848 Sina Weibo posts related to public events were used to evaluate the five emotion schemes: SemEval’s four emotions, Ekman’s six basic emotions, ancient China’s Seven Emotions, Plutchik’s eight primary emotions, and GoEmotions’ 27 emotions.ResultsThe AHP evaluation result shows that Ekman’s scheme had the highest score. The multi-dimensional scaling (MDS) analysis shows that Ekman, Plutchik, and the Seven Emotions are relatively similar. We analyzed Ekman’s six basic emotions in relation to the emotion categories of the other schemes. The correspondence analysis shows that the Seven Emotions’ joy aligns with Ekman’s happiness, love demonstrates a significant correlation with happiness, but desire is not significantly correlated with any emotion. Compared to Ekman, Plutchik has two more positive emotions: trust and anticipation. Trust is somewhat associated with happiness, but anticipation is weakly associated with happiness. Each emotion of Ekman’s corresponds to several similar emotions in GoEmotions. However, some emotions in GoEmotions are not clearly related to Ekman’s, such as approval, love, pride, amusement, etc.ConclusionEkman’s scheme performs best under the evaluation framework. However, it lacks sufficient positive emotion categories for the corpus.

Predicting Mental Health Disorders based on Sentiment Analysis

The increasing prevalence of mental health disorders such as anxiety, depression, and stress calls for innovative, data- driven approaches to early detection and intervention. This research investigates the use of sentiment analysis to predict mental health disorders from social media text, utilizing machine learning techniques to enhance the accuracy and interpretability of mental health classification. We developed and evaluated multiple machine learning models, including Random Forest, Extra Trees, AdaBoost, and Logistic Regression, using a curated dataset of user-generated content reflecting various mental health states. Our rigorous experimentation demonstrates the potential of sentiment analysis combined with advanced machine learning models in identifying mental health conditions. The study highlights that while Random Forest and Extra Trees excel in prediction accuracy, Logistic Regression offers a balanced trade-off between performance and model stability, making it suitable for real-world applications. These findings contribute to the growing field of AI-driven mental health assessment, offering a foundation for integrating multimodal data, model interpretability, and ethical implementation. Keywords: Mental health disorders, Sentiment analysis, Natural language processing, Machine learning

Developing films to support vaccine-hesitant, ethnically diverse parents’ decision-making about the human papillomavirus (HPV) vaccine: a codesign study

ObjectiveTo illustrate an evidence-, theory- and person-based approach to codesign the COMMUNICATE films that support parental decision-making about the human papillomavirus (HPV) vaccine for their teenagers.DesignCodesign study.SettingLocalities covered by two...

User Stress Detection Using Social Media Text: A Novel Machine Learning Approach

This paper introduces a novel Attention-based Bidirectional Long Short-Term Memory (Bi- LSTM) model for detecting stress in social media text, aiming to enhance mental health monitoring in the digital age. Utilizing the unique communicative nature of social media, this study employs user-generated content to analyze emotional and stress levels. The proposed model incorporates an attention mechanism with the Bi-LSTM architecture to improve the identification of temporal features and context relationships in text data, which is crucial for detecting stress indicators. This model stands out by dynamically focusing on text segments that significantly denote stress, thereby boosting the detection sensitivity and accuracy. Through rigorous testing against baseline models such as Text-CNN, LSTM, GRU, and standard Bi-LSTM, our method demonstrates superior performance, achieving the highest F1-score of 81.21%. These results underscore its potential for practical applications in mental health monitoring where accurate and timely detection of stress is essential.

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.

GPT-4 as an X data annotator: Unraveling its performance on a stance classification task.

Data annotation in NLP is a costly and time-consuming task, traditionally handled by human experts who require extensive training to enhance the task-related background knowledge. Besides, labeling social media texts is particularly challenging due to their brevity, informality, creativity, and varying human perceptions regarding the sociocultural context of the world. With the emergence of GPT models and their proficiency in various NLP tasks, this study aims to establish a performance baseline for GPT-4 as a social media text annotator. To achieve this, we employ our own dataset of tweets, expertly labeled for stance detection with full inter-rater agreement among three annotators. We experiment with three techniques: Zero-shot, Few-shot, and Zero-shot with Chain-of-Thoughts to create prompts for the labeling task. We utilize four training sets constructed with different label sets, including human labels, to fine-tune transformer-based large language models and various combinations of traditional machine learning models with embeddings for stance classification. Finally, all fine-tuned models undergo evaluation using a common testing set with human-generated labels. We use the results from models trained on human labels as the benchmark to assess GPT-4's potential as an annotator across the three prompting techniques. Based on the experimental findings, GPT-4 achieves comparable results through the Few-shot and Zero-shot Chain-of-Thoughts prompting methods. However, none of these labeling techniques surpass the top three models fine-tuned on human labels. Moreover, we introduce the Zero-shot Chain-of-Thoughts as an effective strategy for aspect-based social media text labeling, which performs better than the standard Zero-shot and yields results similar to the high-performing yet expensive Few-shot approach.

Analyzing public sentiment on sustainability: A comprehensive review and application of sentiment analysis techniques

In the contemporary context of escalating environmental concerns, understanding public sentiment toward sustainability initiatives is crucial for shaping effective policies and practices. This research explores the efficacy of sentiment analysis in mining social media data to gauge public attitudes toward sustainability efforts. This study employs a variety of machine learning and deep learning models to perform sentiment analysis utilizing a dataset comprising tweets related to human perception towards environmental sustainability. The aim is to transform unstructured social media text into structured sentiment scores. The comparative analysis includes pre-trained sentiment analysis models like VADER, TextBlob, and Flair with traditional machine learning models such as Logistic Regression, SVM, Decision Tree, Naive Bayes, Random Forest, alongside advanced deep learning techniques like LSTM and pre-trained models BERT and GPT-2. Our results reveal significant variations in model performance, underscoring the importance of selecting appropriate sentiment analysis tools that align with the nuanced domain of sustainability. The study further emphasizes the role of transparent and reproducible research practices in advancing trustworthy AI applications. By providing insights into public opinions on sustainability, this research contributes to the broader discourse on leveraging AI to foster environmental responsibility and action. This work not only illustrates the potential of sentiment analysis in understanding public discourse but also highlights the critical need for tailored approaches that consider the specificity of the sustainability context.

Extracting geo-references from social media text using bi-long short term memory networks

<p>The social media data provides great source of information about global and local events, with millions of users. More precisely, the fact that brief messages are practical and are highly popular. Many recent studies have been motivated to estimate the location of the events identified by tracking posts in social media text messages. It might be difficult to extract location data and estimate the location of an event while maintaining a sufficient level of situation awareness, particularly in disaster situations like fires or traffic accidents. In this presented work we proposed an approach to identify geo-references in the text messages. We used bi-directional long short term memory (LSTM) neural networks to extract location information in the text messages. The results show that applying Bi-LSTM on dataset gives high level accuracy after fine-tuning (up to 10 epochs). The testing results show that accuracy achieved is 0.98 and 0.076 loss value. This proves that the proposed methodology is better than the previous conditional random field (CRF)-based approaches.</p>

A novel ensemble model for emotion classification in social media text

Social media provides people with a platform to share their experiences and perspectives, and text is the most common way as either posts or comments. Much emotion-related information, such as mental state and attitude, can be revealed through texts. As a result, text-based emotion analysis plays an important role. This paper aims to propose a new classification model using the ensemble learning method, which can classify the emotions detected from the text into six classes, including joy, fear, surprise, love, sadness, and anger. Multiple base models are trained at the first stage, including traditional machine learning models (Multinomial Naive Bayes, SVM, and Decision Tree) and deep learning models (CNN, LSTM, and GRU). Then, a new ensemble model using the stacking method is developed. The stacking of deep learning models and SVM has achieved the best classification performance, where the accuracy and F1 score are 0.8875 and 0.8410, respectively. The evaluation metrics demonstrate the effectiveness and robustness of the new ensemble model for this emotion classification task.

“New Sincerity” in Social Media Texts: Intentions, Effects and Speech Features

The article presents the results of a study on the phenomenon of “new sincerity” examined on the material of posts on social networks (about 2 thousand contexts in total). It has been noticed that while in registered media the phenomenon mainly exists as initiated by the journalist (in the genres of interviews with famous people), in social media it acts as an initiative of the author. The object of the study was the intentions of the authors of the posts, manifested in their speech, as well as the feedback that the authors received in response to their confession. The discursive approach used in the study has demonstrated the correlation between the topics of confessional posts and the general tasks of public social networks, between author’s intentions and word usage. Thus, feminist public accounts are created specifically to demonstrate those aspects of women’s life in society that have not been publicly discussed before. Borrowed vocabulary is widely used in such cases, as well as words that belong to the field of psychotherapy. Confessional posts on the authors’ personal accounts are much rarer, more varied in topic, most often aimed at creative self-expression and focused on a circle of familiar people. The types of addressees’ reactions to confessional posts are characterized: from distrust of what has been said to support with a demonstration of their similar experience and advice. The research contributes to the development of communication studies in general and media text linguistics in particular.

Emotion Detection inArabic Text in Social Media: A Brief Survey

Emotion detection in Arabic text in social media has gained significant attention due to the increasing use of social media platforms in the Arab world. It is a special case of affective computing that relies on natural language processing techniques to recognize emotions from written text. This article provides a comprehensive review of different approaches used in developing models for emotion detection in Arab textual data in social media. Social media have a substantial impact on societies and have contributed significantly to many fields (marketing, recommendation systems, etc.). Arabic language texts on social networking sites in all their forms (posts -comments -messages -any other form) express the personal feelings of the person concerned; if they are understood correctly, the understanding of the written text will be correct. Scientific research has recently increased in this field to determine people's feelings through their writing of texts. In addition, we have highlighted the utilization of deep learning architectures in the improvement of the performances of models for different types of deep learning models.