Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
13 results
Search Results
Item Honour, hate and violence in social media: Insights from India(Inderscience Publishers, 2019) Chetty, N.; Alathur, S.Honour-based hate content is predominantly generated from family hate content and may affect humanity. In the Indian context, analysis of multiple resources such as literature, reported articles and social media sites pertinent to honour-based hate content is less. Therefore, the purpose of this paper is to identify and understand the influencing factors and emotions of honour-based hate content. A review of literature, news articles on honour killing and the analysis of Twitter content are made to attain the purpose. In India, factor like marrying a person against family members' ideologies is observed as dominating among other factors of honour-based hate content. It has been also observed that emotions such as anger, fear, disgust and sadness are used to express hate. Possible impacts of honour-based hate content on family and society are discussed. The analysis of emotions about honour and hate content increases novelty of the article. © 2019 Inderscience Enterprises Ltd.Item Social media games: Insights from Twitter analytics(Inderscience Publishers, 2020) Pai, R.R.; Alathur, S.The addiction to online games and chat rooms has created a negative impact on human health by increasing the level of stress, anxiety, and aggression. Social media games are the one which was taken over various forms of engagement in the recent years with a greater number of reported evidence and deaths of youth population across the world. Many people had posted their emotions about this game in all social media, which had created a large amount of data. In this paper, we had tried to study the sentiment of the people by extracting 4,429 tweets. The results of the analysis indicate that the peoples' perception towards this game is progressing in a positive direction due to the various policy implementations and controlling mechanisms supporting people from self-harm practices. Following a complex adaptive system approach for our results, this paper also explains the causal relationships between various components of isolation and problematic content on self-harm practices. © 2020 Inderscience Enterprises Ltd.Item International efforts for children online safety: A survey(Inderscience Publishers, 2020) Andrews, D.; Alathur, S.; Chetty, N.Children online safety is a global issue and attaining international attention to address it. Often, children are vulnerable to online threats. Aim of this paper is to review children online safety issues and identify existing international efforts for reducing online risks. In this regard, efforts from available international bodies for providing online safety to children are reviewed and reported. To overcome online risks, understanding the behaviour of online ecosystem and coping after facing risks are most important. The ecosystem involves different stakeholders such as service providers, physical network, online users being connected, social media sites and tools and technology. Elimination of online risks is difficult but the intensity of risks can be reduced. © © 2020 Inderscience Enterprises Ltd.Item Text-mining-based Fake News Detection Using Ensemble Methods(Chinese Academy of Sciences, 2020) Reddy, H.; Raj, N.; Gala, M.; Annappa, A.Social media is a platform to express one’s views and opinions freely and has made communication easier than it was before. This also opens up an opportunity for people to spread fake news intentionally. The ease of access to a variety of news sources on the web also brings the problem of people being exposed to fake news and possibly believing such news. This makes it important for us to detect and flag such content on social media. With the current rate of news generated on social media, it is difficult to differentiate between genuine news and hoaxes without knowing the source of the news. This paper discusses approaches to detection of fake news using only the features of the text of the news, without using any other related metadata. We observe that a combination of stylometric features and text-based word vector representations through ensemble methods can predict fake news with an accuracy of up to 95.49%. © 2020, Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature.Item An architecture for digital hate content reduction with mobile edge computing(Chongqing University of Posts and Telecommunications, 2020) Chetty, N.; Alathur, S.Mobile devices with social media applications are the prevalent user equipment to generate and consume digital hate content. The objective of this paper is to propose a mobile edge computing architecture for regulating and reducing hate content at the user's level. In this regard, the profiling of hate content is obtained from the results of multiple studies by quantitative and qualitative analyses. Profiling resulted in different categories of hate content caused by gender, religion, race, and disability. Based on this information, an architectural framework is developed to regulate and reduce hate content at the user's level in the mobile computing environment. The proposed architecture will be a novel idea to reduce hate content generation and its impact. © 2019 Chongqing University of Posts and TelecommunicationsItem Social media and disaster management: influencing e-participation content on disabilities(Emerald Group Holdings Ltd., 2021) Alathur, S.; Kottakkunnummal, M.; Chetty, N.Purpose: This study aims to analyse the nature and forms of digital content that may influence e-participation for persons with disabilities (PWDs) during a flood disaster. Design/methodology/approach: This paper undertakes a case study of the 2019 and 2020’s flood in Kerala, India. In-depth interviews with rehab workers during the flood are used in the study. Topic modelling and sentiment analysis are carried out using Twitter data. The native language responses from Facebook forums related to PWDs are analysed manually to construct taxonomy of problematic content Findings: The results show that problematic content toward PWDs in the social media occurs during a flood. The extreme and exploitative content results in disability exclusion. Thus, e-participants fail to address the actual disability-specific requirements through social media during a disaster. Research limitations/implications: The paper explores social media content toward PWDs. Implications of findings on citizens’ e-participation competency are delineated. Existing e-participation literature reports a low degree of disability e-participation in social media. Exploring disability e-participation helps to design more inclusive participation platforms. Further studies can explore the disability consciousness among e-participants for a more inclusive space. Practical implications: The development of problematic content in the social media environment is alarming. Regulatory frameworks are also less adequate. Hence, policies for enabling inclusive participation that is not limited to the information technology infrastructure is needed. Social implications: First, the citizens will get more insights for meaningful disability e-participation. Second, inclusive e-participation platform designs will help to reduce problematic content generation. Originality/value: Disability e-participation requires regional studies. But there are fewer studies on disability e-participation from developing nations. The current study considered the regional context and complexities of disability e-participation. This paper gives policy recommendations for an inclusive e-participation. © 2021, Emerald Publishing Limited.Item A transformer-based architecture for fake news classification(Springer, 2021) Mehta, D.; Dwivedi, A.; Patra, A.; Anand Kumar, M.In today’s post-truth world, the proliferation of propaganda and falsified news poses a deadly risk of misinforming the public on a variety of issues, either through traditional media or on social media. Information people acquire through these articles and posts tends to shape their world view and provides reasoning for choices they take in their day to day lives. Thus, fake news can definitely be a malicious force, having massive real-world consequences. In this paper, we focus on classifying fake news using models based on a natural language processing framework, Bidirectional Encoder Representations from Transformers, also known as BERT. We fine-tune BERT for specific domain datasets and also make use of human justification and metadata for added performance in our models. We determine that the deep-contextualizing nature of BERT is effective for this task and obtain significant improvement over binary classification, and minimal yet important improvement in six-label classification in comparison with previously explored models. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.Item Do Social Media and e-WOM Influence M-Government Services? A Citizen Perspective From India(IGI Global, 2022) Hebbar, S.; Kiran, K.B.In Web 4.0 technologies, social media (SM) has emerged as a prominent tool for the government to interact and engage with citizens. It is also an effective channel for providing government services. However, for effective implementation and its success, it is critical to understand the citizens' perceptions towards the government's use of SM and its impact on mobile government (MG) adoption. Consequently, the study focuses on assessing the impact of SM influence and electronic word of mouth (e-WOM) on MG service parameters such as MG awareness, MG transparency, and MG trust. The results of structural equation modelling revealed the significance of e-WOM on improving MG awareness and trust and SM influence. Further, SM influence had a direct impact only on MG transparency. However, results revealed the importance of SM influence and MG transparency as a mediator for MG trust. Gender and age as moderators are investigated and discussed in detail. © © 2022, IGI Global.Item Profile generation from web sources: an information extraction system(Springer, 2022) Ranjan, R.; Vathsala, H.; Koolagudi, S.G.The Internet space has a vast collection of information which is not always structured. These sources of information such as social media, news articles, blogs, speeches and videos often contain information that could be utilized to generate decision making tools such as reports about events and individuals. Using this information is a long and tedious process if done manually. Over the years, a lot of research has been done in data mining and natural language processing techniques to facilitate the consumption of this vast amount of data. The current work describes ProfileGen, an information extraction system that uses a variety of these data sources to form a profile of a given person. There are two parts to this application: The first part uses information publicly available on social media sites, news articles on news websites and blogs and compiles this information to form a corpus about the given person, and in the second part, the information is ranked using machine learning techniques, so as to provide information in the order of importance. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.Item Transfer learning based code-mixed part-of-speech tagging using character level representations for Indian languages(Springer Science and Business Media Deutschland GmbH, 2023) Anand Kumar, A.K.; Padannayil, S.K.Massive amounts of unstructured content have been generated day-by-day on social media platforms like Facebook, Twitter and blogs. Analyzing and extracting useful information from this vast amount of text content is a challenging process. Social media have currently provided extensive opportunities for researchers and practitioners to do adequate research on this area. Most of the text content in social media tend to be either in English or code-mixed regional languages. In a multilingual country like India, code-mixing is the usual fashion witnessed in social media discussions. Multilingual users frequently use Roman script, an convenient mode of expression, instead of the regional language script for posting messages on social media and often mix it with English into their native languages. Stylistic and grammatical irregularities are significant challenges in processing the code-mixed text using conventional methods. This paper explains the new word embedding via character level representation as features for POS tagging the code-mixed text in Indian languages using the ICON-2015, ICON-2016 NLP tools contest data set. The proposed word embedding features are context-appended, and the well-known Support Vector Machine (SVM) classifier has been used to train the system. We have combined the Facebook, Twitter, and WhatsApp code-mixed data of three Indian languages to train the Transfer learning based language-independent and source independent POS tagging. The experimental results demonstrated that the proposed transfer method achieved state-of-the-art accuracy in 12 systems out of 18 systems for the ICON data set. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.