The problem of detecting bots, automated social media accounts governed by software but disguising as human users, has strong implications. For example, bots have been used to sway political ...elections by distorting online discourse, to manipulate the stock market, or to push anti-vaccine conspiracy theories that may have caused health epidemics. Most techniques proposed to date detect bots at the account level, by processing large amounts of social media posts, and leveraging information from network structure, temporal dynamics, sentiment analysis, etc. In this paper, we propose a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level: contextual features are extracted from user metadata and fed as auxiliary input to LSTM deep nets processing the tweet text. Another contribution that we make is proposing a technique based on synthetic minority oversampling to generate a large labeled dataset, suitable for deep nets training, from a minimal amount of labeled data (roughly 3000 examples of sophisticated Twitter bots). We demonstrate that, from just one single tweet, our architecture can achieve high classification accuracy (AUC > 96%) in separating bots from humans. We apply the same architecture to account-level bot detection, achieving nearly perfect classification accuracy (AUC > 99%). Our system outperforms previous state of the art while leveraging a small and interpretable set of features, yet requiring minimal training data.
Using expert interviews and focus groups, this book investigates the theoretical and practical intersection of misinformation and social media hate in contemporary societies. Social Media and Hate ...argues that these phenomena, and the extreme violence and discrimination they initiate against targeted groups, are connected to the socio-political contexts, values and behaviours of users of social media platforms such as Facebook, TikTok, ShareChat, Instagram and WhatsApp. The argument moves from a theoretical discussion of the practices and consequences of sectarian hatred, through a methodological evaluation of quantitative and qualitative studies on this topic, to four qualitative case studies of social media hate, and its effects on groups, individuals and wider politics in India, Brazil, Myanmar and the UK. The technical, ideological and networked similarities and connections between social media hate against people of African and Asian descent, indigenous communities, Muslims, Dalits, dissenters, feminists, LGBTQIA communities, Rohingya and immigrants across the four contexts is highlighted, stressing the need for an equally systematic political response. This is an insightful text for scholars and academics in the fields of Cultural Studies, Community Psychology, Education, Journalism, Media and Communication Studies, Political Science, Social Anthropology, Social Psychology, and Sociology.
In this issue of the Journal of Medical Internet Research, the World Health Organization (WHO) is presenting a framework for managing the coronavirus disease (COVID-19) infodemic. Infodemiology is ...now acknowledged by public health organizations and the WHO as an important emerging scientific field and critical area of practice during a pandemic. From the perspective of being the first "infodemiologist" who originally coined the term almost two decades ago, I am positing four pillars of infodemic management: (1) information monitoring (infoveillance); (2) building eHealth Literacy and science literacy capacity; (3) encouraging knowledge refinement and quality improvement processes such as fact checking and peer-review; and (4) accurate and timely knowledge translation, minimizing distorting factors such as political or commercial influences. In the current COVID-19 pandemic, the United Nations has advocated that facts and science should be promoted and that these constitute the antidote to the current infodemic. This is in stark contrast to the realities of infodemic mismanagement and misguided upstream filtering, where social media platforms such as Twitter have advertising policies that sideline science organizations and science publishers, treating peer-reviewed science as "inappropriate content."
U.S. companies spent $5.1 billion on social media advertising in 2013, but a recent Gallup survey revealed that these advertisements had no influence on the majority of U.S. consumers’ buying ...decisions. For social media marketing to be effective, we argue that social media marketing efforts need to be congruent and aligned with the different needs of social media users. To this end, this article presents a typology of current social media services using the following categories: relationship, self-media, collaboration, and creative outlet. We further elaborate on how each type of social media caters to basic human needs, and provide implications for social media marketing based on the need-congruence lens.
The influence of TikTok has reached the news media, which has adapted to the logic of the platform, in a context marked by the incidental consumption of news, virality and the intermediation of ...technology in access to information. The popularity of this social network invites news outlets to address a young audience on a platform characterized by visual and short content and dynamics defined by algorithmic recommendations, trending hashtags and challenges. Based on an exploratory search of news media and programmes on TikTok from around the world, we selected 234 accounts and conducted a content analysis of the 19 news media and programmes identified with a verified profile and general thematic scope. The results point to a progressive incorporation of the media since 2019, with the purpose of informing, positioning their brand and adapting to the logic of TikTok in a new approach to journalism for younger generations.
What are the effects of a brand's owned social media? This meta-analysis examines the impact of owned social media on social media engagement and sales. Whereas the findings support some current ...beliefs (e.g., owned social media are more effective to boost sales for new vs. mature products), it highlights several novel insights. Contrary to popular beliefs that owned social media mainly drive engagement and hardly affect sales, the results show the opposite, with an average elasticity of .137 for social media engagement and .353 for sales. In addition, the results suggest ways to better adapt owned social media content to communication goals. To create engagement, content needs to focus on emotional needs and steer away from deals, which are the least effective content type. To stimulate sales, content should be more functional, rather than emotional, in nature and communicate product benefits. Surprisingly, the authors find that growing a large social media community is not essential for boosting sales, as owned social media are more effective for brands with fewer followers. Furthermore, while using one global social media strategy is tempting, owned social media are more effective in countries with high power distance, calling for a less uniform approach.