Figure - uploaded by Farzana Kabir Ahmad
Content may be subject to copyright.
Methods and Techniques for social tension detecton
Source publication
The trend of people in using social media services to share
personal thoughts has caused textual data to grow
exponentially. However, uncontrolled negative discussions
on social media can lead to generating social tension and
facilitate public gathering in real life. User generated
contents on social media can be explored to reveal insights to
the...
Contexts in source publication
Context 1
... fact, this study argued that syntactic analysis is not necessary to obtain sufficient classification result if large data is provided for training and testing phase. Table 1 summarizes the methods and techniques that have been discussed in all approaches. ...Similar publications
The exponential growth of multimodal content across social media platforms, comprising text, images, audio, and video, has catalyzed substantial interest in artificial intelligence, particularly in multi-modal sentiment analysis (MSA). This study presents a comprehensive survey of 30 research papers published between 2020 and 2024 by eminent publis...
![Fig. 2: Comparison of different machine learning methods [1]](profile/Seifeldin-Abdelghany/publication/353549852/figure/fig1/AS:1050880665198594@1627560883790/Comparison-of-different-machine-learning-methods-1_Q320.jpg)
![Fig. 3: Machine learning method Steps [2]](profile/Seifeldin-Abdelghany/publication/353549852/figure/fig2/AS:1050880669388800@1627560884208/Machine-learning-method-Steps-2_Q320.jpg)
![Fig. 4: Sentiment results sample [2].](profile/Seifeldin-Abdelghany/publication/353549852/figure/fig3/AS:1050880669413376@1627560884255/Sentiment-results-sample-2_Q320.jpg)
![Fig. 5: Positive [2].](profile/Seifeldin-Abdelghany/publication/353549852/figure/fig4/AS:1050880669384714@1627560884351/Positive-2_Q320.jpg)
![Fig. 6: Negative [2].](profile/Seifeldin-Abdelghany/publication/353549852/figure/fig5/AS:1050880669401089@1627560884395/Negative-2_Q320.jpg)
With the rise of social media, the idea of extracting the emotions of people and their ratings increased. Sentiment analysis is an NLP method that aims to determine the sentiment of a certain text. In this paper, we delve deeper into sentiment analysis. First, we present three papers that discussed sentiment analysis. Then, we compare and contrast...
Sentiment or opinion analysis employs natural language processing to extract a significant pattern of knowledge from a large amount of textual data. It examines comments, opinions, emotions, beliefs, views, questions, preferences, attitudes, and requests communicated by the writer in a string of text. It extracts the writer’s feelings in the form o...
In this paper, we suggest a unique method for implementing text embedding that combines a large language model with the Retrieval Augmented Generation (RAG) model. Text embedding is essential in many natural language processing applications, including question-answering, sentiment analysis, and information retrieval. Conventional techniques for tex...
Given the exponential growth of eWOM, especially among the millennial generation, an analysis of the consultation behaviour of online opinions is essential to better understanding the decision-making process. The aim of this proposal is to analyse how the motivations towards eWOM consultation contribute to the final adoption of eWOM, especially in...
Citations
... The increasing volume of user-generated content (UGC) on social media platforms provides a vast amount of data, which can be accessed and explored to understand patterns of human emotions, behaviours, and sentiments [9]. With these data, Machine Learning approaches such as Support Vector Machine (SVM) and Random Forest (RF) can utilize the data to perform predictions [10]. ...
Social media services have become a prevalent communication tool due to their capability to instantly share information with a large number of people for free. However, social media also facilitate cyberbullying, and studies have shown that cyberbullying on social media has a severe impact compared to other platforms. In some cases, cyberbullying provokes tragic problems, such as suicide. The information shared on social media services provides a massive amount of textual data, which can be used to explore patterns of human behaviors including cyberbullying. This paper aims to build a dataset of offensive language for research on cyberbullying in the Malay language through a series of baseline experiments by implementing SVM classifiers. These preliminary experiments helped to understand the performance of automatic tools that mine for abusive language within a corpus of Malay texts. To achieve the objectives, social media extraction methods and new crawling technologies oriented have been developed to monitor the Instagram accounts of popular Malaysian celebrities. The resulting collection contains 165,239 real-world comments associated with 27 Instagram public accounts. A sample of this corpus was manually labelled in terms of cyberbullying categories. After the dataset was cleaned, normalized, and vectorized, this led to a collection of 527 comments. Following a standard training (70%) and test (30%) split, the SVM classifier was developed and evaluated. These initial experiments produced a model accuracy of 75% and f1-scores of around 75%.
The purpose of this study is to develop a method for automatic detection of hotbeds of social tension on the Internet. The main problem with such detection is that currently there is no general methodology for detecting signs of social tension in the digital space, while more and more communication processes are moving to the network. Within the framework of this study, based on the analysis of sources, attributes of social tension were formed that are characteristic of expression in the digital space. Cognitive models and an ontology of attributes were developed, on the basis of which attributes of social tension, characteristic of the initial stages of the development of the situation, were formed. The formed complex of attributes is based on the methods of automatic detection of psychoemotional states of the individual. The developed method of automatic social tension detection on the Internet makes it possible to detect hotbeds of information dissemination that are suspicious from the point of view of intensifying social tension with the aim of further information countermeasures.
KeywordsEdge computingReliabilityDistributed systemsReconfigurationInformation systems managementDecentralized controlDistributed leader
