Finding Qs: Profiling QAnon Supporters on Parler

This study aims to explore the cultural and social factors and dimensions identified by social identity theory, public sphere theory, and self-presentation theory that influence interaction through social media platforms in Saudi society. This study is based on several theoretical frameworks that address cultural and social dimensions, as well as audience interaction with media and communication content. Among these frameworks are identity theory and public sphere theory, which help understand the components of identity in the social environment. Public sphere theory, in particular, is based on the fundamental premise that "the public is active" in its ability to dialogue and debate issues of interest, which contributes to shaping public opinion that guides attitudes toward these issues. Despite the public's ability to interact, its interaction is influenced by underlying social and cultural structures, as framed by identity and public sphere theories. These frameworks shape the criteria for audience engagement and interaction with media and communication messages across social media platforms. It also discusses self-presentation theory, whereby individuals seek to manage how they present themselves on social media platforms by engaging with various societal issues. Accordingly, the research examines the impact of these factors on the nature and extent of engagement across different forms of social media engagement, and assesses the degree to which these factors shape the level and nature of user engagement with content posted on social media platforms.

Network versus content: The effectiveness in identifying opinion leaders in an online social network with empirical evaluation

Exploring the role of sentiment analysis with network and temporal features for finding influential users in social media platforms

Journal article titles serve as both the introduction to the substance of articles and incentives for users to read articles in their entirety, but different quality articles may use different linguistic and content features of titles. This is rarely investigated by discourse analysts. The goal of this research is to compare and contrast titles in the English education field written by Indonesian authors and published in local journals with those written by foreign authors and published in high-impact foreign journals. Two hundred and eight article titles from five different Indonesian-accredited local journals and 512 article titles from five different high-impact foreign journals form the corpus of this research. The analyses were done on the titles' length and their linguistic and content features. The findings show that the article titles in high-impact foreign journals are slightly longer than those in local journals, local authors use nominal construction and verb-ing phrase types more frequently than high-impact foreign authors do, foreign authors use full sentences and prepositional phrases more frequently than the local journal authors do, and high-impact foreign journals use topic-only type of titles more frequently than in local journals do. The similarities are that nominal and compound constructions are the most dominant linguistic features while topic-only and method categories are the most dominant content features in both groups of article titles. While the most important features of titles are probably the conciseness and preciseness of the information contained in the titles, future studies should investigate these aspects of journal article titles in the same or different fields.

To what extent user's stance towards a given topic could be inferred? Most of the studies on stance detection have focused on analysing user's posts on a given topic to predict the stance. However, the stance in social media can be inferred from a mixture of signals that might reflect user's beliefs including posts and online interactions. This paper examines various online features of users to detect their stance towards different topics. We compare multiple set of features, including on-topic content, network interactions, user's preferences, and online network connections. Our objective is to understand the online signals that can reveal the users' stance. Experimentation is applied on tweets dataset from the SemEval stance detection task, which covers five topics. Results show that stance of a user can be detected with multiple signals of user's online activity, including their posts on the topic, the network they interact with or follow, the websites they visit, and the content they like. The performance of the stance modelling using different network features are comparable with the state-of-the-art reported model that used textual content only. In addition, combining network and content features leads to the highest reported performance to date on the SemEval dataset with F-measure of 72.49%. We further present an extensive analysis to show how these different set of features can reveal stance. Our findings have distinct privacy implications, where they highlight that stance is strongly embedded in user's online social network that, in principle, individuals can be profiled from their interactions and connections even when they do not post about the topic.

Sociolinguistic styles and the resultant ascribed identities are understood as the product of simultaneous variables, leading to the notion of bricolage, or the co-occurrence of variables and their collective indexical meanings. Relatively little attention has been paid to these processes as they manifest on social media platforms. The goal of the current paper is to understand which linguistic and thematic features co-occur in the online production of the no sabo kid style and identity, which manifests as a form of linguistic discrimination towards U.S. Latinx youth. “Hashtag communities” were used to locate posts about no sabo kids on TikTok (N = 95), and videos were automatically and manually coded for salient linguistic and discursive resources in the online no sabo kid community. The results show the co-occurrence of code-switching and phonological and lexical variation, alongside discursive themes, namely ‘proficiency’, ‘ethnicity’, and ‘performative lexical gaps’. I argue that the no sabo kid hashtag community is a mediated manifestation of ideologies surrounding U.S. Latinx bilinguals, where a supposed lack of proficiency in Spanish and grammatical blending of Spanish and English index inauthentic ethnicity. Mediated instantiations of sociolinguistic styles shed light on how linguistic features become enregistered through multimodality and semiotic bricolage.

We present experimental results on the task of automatically predicting group members' attitudes about management of their meeting, based on linguistic and acoustic features derived from the meeting recordings and transcripts. The group members' attitudes were gathered from detailed post-meeting questionnaires. A key finding is that features of linguistic content by themselves yield poor prediction performance on this task, but the best results are found by combining acoustic and linguistic features in a multimodal prediction model. When trying to automate the detection of group member attitudes that might be manifested subtly in their language and behaviour, a multimodal analysis is key.

This chapter examines the phenomenon of internet users attempting to report and prevent online child sexual exploitation (CSE) and child sexual abuse material (CSAM) in the absence of adequate intervention by internet service providers, social media platforms, and government. The chapter discusses the history of online CSE, focusing on regulatory stances over time in which online risks to children have been cast as natural and inevitable by the hegemony of a “cyberlibertarian” ideology. We illustrate the success of this ideology, as well as its profound contradictions and ethical failures, by presenting key examples in which internet users have taken decisive action to prevent online CSE and promote the removal of CSAM. Rejecting simplistic characterizations of “vigilante justice,” we argue instead that the fact that often young internet users report feeling forced to act against online CSE and CSAM undercuts libertarian claims that internet regulation is impossible, unworkable, and unwanted. Recent shifts toward a more progressive ethos of online harm minimization are promising; however, this ethos risks offering a new legitimizing ideology for online business models that will continue to put children at risk of abuse and exploitation. In conclusion, we suggest ways forward toward an internet built in the interests of children, rather than profit.

The use of social media, like Facebook, Twitter and LinkedIn, is nowadays very common and quite for sure each one of us has at least a digital profile on them. The information left of these platforms such as likes, posts, tweets and photos are very informative and can be used for deducting our preferences, tendencies and behaviors. The analysis of the social media footprints has become a relevant research topic in the last decade and many works have demonstrated how to extract some traits of the user's affective sphere. In this paper, we focus on the prediction of empathic tendencies of a subject as an index of the influence of emotions during decisional processes. This value can be included in the user profile and can be relevant in some scenarios, such as music and movie recommender systems, where the emotional component is strongly delineated. We propose an approach of empathy level prediction based on a linear regression algorithm over Facebook profiles. We use a word2vec representation of the textual contents of the user's time-line posts, a LDA and SVD vector representation of the user's likes and other general descriptive data. The evaluation performed has demonstrated the validity of the approach for predicting the empathy tendency and the results have showed some relevant correlations with some specific groups of user's descriptive features.

Trust prediction in online social networks is crucial for information dissemination, product promotion, and decision making. Existing work on trust prediction mainly utilizes the network structure or the low-rank approximation of a trust network. These approaches can suffer from the problem of data sparsity and prediction accuracy. Inspired by the homophily theory, which shows a pervasive feature of social and economic networks that trust relations tend to be developed among similar people, we propose a novel deep user model for trust prediction based on user similarity measurement. It is a comprehensive data sparsity insensitive model that combines a user review behavior and the item characteristics that this user is interested in. With this user model, we firstly generate a user's latent features mined from user review behavior and the item properties that the user cares. Then we develop a pair-wise deep neural network to further learn and represent these user features. Finally, we measure the trust relations between a pair of people by calculating the user feature vector cosine similarity. Extensive experiments are conducted on two real-world datasets, which demonstrate the superior performance of the proposed approach over the representative baseline works.

Depression is a complicated mental health disorder with many different forms and symptoms. Traditional methods face barriers when detecting and diagnosing depression, including social stigma and societal labeling. As social media platforms became commonplace for information sharing, their anonymity meant that the barriers had considerably lessened. An alternative method to depression detection being researched is using social media data to build machine learning models for depression detection. To that end, this research uses machine learning models to incorporate new user networks and user engagement features into depression detection on Twitter users. These two features provide an additional understanding of users and may significantly affect depression detection. A Twitter dataset is constructed to include additional data on users' following list and the history of liked tweets not examined in prior studies. Ten machine learning models are constructed using five different machine learning algorithms tested on two sets of features. Models with proposed features outperformed other machine learning models without proposed features, with the best model yielding 82.05% performance for both accuracy and F1 score. This study discovered that the most important feature is the number of depression keywords in liked tweets, with at least twice the gain compared to 88% of other features used. Topic modelling features for liked tweets also have high gain and are important in detecting depression. Additionally, features derived from original tweets, replies, and liked tweets have higher gain and are more important than retweets and quote tweets in detecting depression.

Language users, in our contemporary world, fail to put into cognisance the distinctive linguistic features that characterise each communicative event, often blurring the lines between situational contexts. This is partly owing to exposure to diverse language varieties and the prevalence of digital communication such as texting, and social media. This study undertakes a comparative register analysis of language use on social media platforms and in academic writing, with a view to examining the idiosyncratic features of each of these genres of writings which will enable language users adapt linguistic features to suit these disparate contexts. Using Biber and Conrad’s (2009) analytical framework, the study focuses on aspects such as vocabulary, syntax, and tone, seeking to identify patterns of language use that are unique to each register or shared across contexts. Findings reveal that while the distributions of prepositions and conjunctions are almost similar in both the registers of academic writing and social media messages, the register of social media messages makes use of linguistic features such as pronouns, verbs and adverbs more than the register of academic writing, thereby disclosing that the conversational properties of informal tone, personalisation, action-dependence and emphasis are more prominent in social media language. By exploring the intersections and divergences between social media language and academic writing, this research aims to inform strategies for adapting language to context, ultimately enhancing clarity, coherence, and overall effectiveness of communication.

This study analyzed the linguistic features in Qur’anic translation in the Al Fatihah Surah. It compares five different translations, namely, Asad Quran Translation, Malik Quran Translation, Yusuf Ali Quran Translation, and Piktal Quran Translation. The analysis uses both qualitative and quantitative approaches. The theoretical framework of the study is based on Newmark's (1988) multidisciplinary method of translation. Results of the study showed that varied translation versions of Qur’an verses should be analyzed to transfer and reduce original meaning to non-native speakers of the Arabic language since Qur’an includes stylish features in both form and content. In addition, findings revealed that translation of linguistic features postures challenges translators while interpreting meaning. This study concludes that most of the linguistic features under scrutiny have been rendered into English that is often erroneous. However, the conceptualization of linguistic features in Qur’anic translation is often lost. Keywords : Linguistic features. phonic, Qur’an translation, Al Fatihah DOI: 10.7176/JLLL/87-05 Publication date: April 30 th 2022

The rapid spread of misinformation on social media platforms, especially Twitter, presents a challenge in the digital age. Traditional fact-checking struggles with the volume and speed of misinformation, while existing detection systems often focus solely on linguistic features, ignoring factors like source credibility, user interactions, and context. Current automated systems also lack the accuracy to differentiate between genuine and fake news, resulting in high rates of false positives and negatives. This study investigates the creation of a Twitter bot for detecting fake news using deep learning methodologies. The research assessed the performance of BERT, CNN, and Bi-LSTM models, along with an ensemble model combining their strengths. The TruthSeeker dataset was used for training and testing. The ensemble model leverages BERT's contextual understanding, CNN’s feature extraction, and Bi-LSTM’s sequence learning to improve detection accuracy. The Twitter bot integrates this ensemble model via the Twitter API for real-time detection of fake news. Results show the ensemble model significantly outperformed individual models and existing systems, achieving an accuracy of 98.24%, recall of 98.14%, precision of 98.42%, and an F1-score of 98.24%. These findings highlight that combining multiple models can offer an effective solution for real-time detection of misinformation, contributing to efforts to combat fake news on social media platforms.

With the rapid development of social media and the increasing scale of social media data, the rumor detection on social media platforms has become vitally crucial. The key challenges for rumor detection on social media platforms are how to identify rumors deeply entangled with the specific content and how to detect rumors for the emerging social media events without labeled data. Unfortunately, most of the existing approaches can hardly handle these challenges since they tend to learn event-specific features and cannot transfer the learned features to newly emerged events. To tackle the above challenges, we propose a novel Multimodal Disentangled Domain Adaption (MDDA) method which can derive event-invariant features and thus benefit the detection of rumors on emerging social media events. The model consists of two components: the multimodal disentangled representation learning and the unsupervised domain adaptation. The multimodal disentangled representation learning is responsible for disentangling the multimedia posts into the content features and the rumor style features, and removing the content-specific features from post representation. The unsupervised domain adaptation aims to filter out the event-specific features and keep shared rumor style features among events. Based on the final event-invariant rumor style features, we train a robust social media rumor detector that can transfer knowledge from source events to the target events, which can perform well on the newly emerged events. Extensive experiments on two Twitter benchmark datasets demonstrate that our rumor detection model outperforms state-of-the-art methods.