2026· International journal of engineering and technology· 0 citations· 7 references
TL;DR
This paper will explore the construction of stance data, the evolution of model paradigms, and the issue of generalization in real-world applications, and propose new theoretical paths to improve the practicality and credibility of this field.
Abstract
— With the widespread adoption of social media, the speed and reach of information dissemination have expanded dramatically in unpredictable ways. This is not merely a simple phenomenon; it is fundamentally changing the way we acquire and process information. Stance detection in social media text is therefore particularly important, especially in rapidly changing and emotionally charged online discussions. Stance detection goes beyond mere sentiment analysis; it involves profoundly analyzing the complex attitudes, stances, and implicit biases embedded in the text. In recent years, with the rapid development of Large Language Models (LLM) and deep learning technologies, traditional stance detection methods have gradually been replaced by more complex and sophisticated techniques, particularly in large-scale text processing, where deep learning plays an increasingly prominent role. This paper will explore the construction of stance data, the evolution of model paradigms, and the issue of generalization in real-world applications. The challenge of stance detection lies not only in accurately identifying stances but also in integrating various factors — such as emotion, culture, and social context — into the model.This paper will analyze this from multiple levels, including data construction and technological changes, and propose new theoretical paths to improve the practicality and credibility of this field.
Examination of sentiment analysis methods applied to social media text data, covering lexicon-based, machine learning, and deep learning approaches, including transformerbased architectures, as well as widely used datasets, shows how sentiment analysis can be applied to the detection of threats that exploit human emotions.
Vusal Shahbazov· “Kibertəhlükəsizlik və rəqəm...· 0 citations
The digital news portals and social media are rapidly expanding, which has significantly increased the spread of fake news, which affects public opinion, social harmony, and trust in information sources. Detection of fake news at an early stage is a critical research challenge. In recent years, researchers have applied multiple methods for the classification of news articles as fake using Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning (DL) techniques. This paper discusses a feature-based analysis of text-oriented fake news detection methods published from 2017 to 2025. The analysis demonstrates how different textual features, such as linguistic, stylistic, psychological, statistical, semantic, and syntactic features, are used for the identification of fake or real news. A comparative analysis of existing studies shows that most research primarily depends on statistical and semantic representations like N-grams, TF-IDF, and word embeddings, whereas linguistic, stylistic, and psychological cues are comparatively less explored. In addition, syntactic features have gained very limited attention despite their potential to enhance detection performance. The review emphasizes integrating multiple feature types to develop more reliable and interpretable detection systems. It also identifies research gaps and suggests future directions for developing comprehensive feature-based frameworks for fake news detection
Unknown authors· International Research Journ...· 0 citations
Social media has become usefull and most important platform for individuals to access news due to its speed and cost-effectiveness of disseminating information on a particular channel. However, these platforms also make it a breeding ground for the spread of fake news, which can impact society and individuals. With the advent of modern technology that comes with the fourth industrial revolution, promoting openness and increased engagement, social media has evolved to serve multiple purposes. It has become an integral part of our lives, beyond what was originally intended for just a small group of people. Consequently, identifying such fake news has become a crucial task for researchers and remains a major concern. This paper aims to examine the methods of publishing and distributing fake news, and outlines the approach of classifying, organizing, and developing algorithms. Our proposed solution is called the "Fake News Detection using Hybrid-kMeans (FNDHKM)" algorithm that utilizes Natural Language Processing (NLP) and machine learning (ML) techniques to detect fake news on social media platforms, specifically Twitter. The experiments were performed on three different datasets obtained from Twitter and involved dimensionality reduction on the extracted data. The highest accuracy achieved was 85% and 90% for precision and accuracy, respectively. The proposed FNDHKM approach showed significantly high accuracy with low overhead.
Shubha Mishra· International journal of com...· 0 citations
As the ecosystem encompassing social media and product reviews grows ever more intricate, emotional expression presents prominent traits including subtlety, sarcasm, fragmentation and multimodal fusion. Traditional machine learning models (e.g., SVM), which rely on manual feature engineering, encounter bottlenecks in recognition accuracy when dealing with irony, metaphor, and long-distance sentiment dependencies. Sentiment analysis of reviews is thus trapped in the dual predicament of "semantic noise" and "shallow understanding." This paper focuses on the advantages and accuracy verification of Large Language Models (LLMs) in tackling high-difficulty sentiment analysis of reviews. This study abandons the mere enumeration of single accuracy values and instead delves into the cognitive breakthroughs of LLMs across three key dimensions: context-aware ambiguous meaning resolution, which deeply interprets ironic and euphemistic connotations; fine-grained sentiment element extraction, accurately identifying the polarity of praise or criticism toward specific product attributes; and closed-loop verification through sentiment generation and explanation, providing traceable justifications via chain-of-thought mechanisms.
Yaxuan Wang· Applied and Computational En...· 0 citations
This review paper looks at transformer-based unified models that incorporate sentiment analysis and false tweet detection, and stresses how transformer-based models, such as BERT, RoBERTa, and XLNet, outperform traditional machine learning algorithms due to their attention mechanisms and contextual knowledge.
Gurpreet Kaur, J. Rana· International Journal for Re...· 0 citations
Social media generates massive amounts of unstructured, multilingual textual data that contain many sentiments, emotions, and opinions from users that provide insights for enterprises undergoing digital transformation. In this paper, we evaluate a variety of commercially available, lightweight large language models (LLMs) for sentiment, emotion, aspect-based sentiment, and toxic speech detection on noisy, real-world social media datasets. These lightweight models are compared (against traditional RoBERTa-based classifiers and heavyweight “pro” LLMs) in terms of performance, latency, and cost trade-offs that are key for scalable deployment across the enterprise. Our results show that lightweight LLMs achieve good accuracy with considerably lower response times and costs, which makes them suitable as the next step in digital transformation for real-time social media analytics. Additionally, we investigate the importance of prompt engineering and show that preprocessing can be very limited for LLMs. This study provides operational guidelines regarding model selection based on latency, accuracy, and cost trade-offs as well as optimal prompt engineering techniques. Finally, it evaluates the intersection of operational performance and resource efficiency to help researchers and developers integrate LLM-based social media analytics into digitized business practices.
Ioannis Kapantaidakis, Ioannis Kopanakis, Emmanouil Perakakis et al.· Applied System Innovation· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
