Refine
Document Type
- Article (10)
- Doctoral Thesis (5)
- Conference Proceeding (3)
- Postprint (3)
- Monograph/Edited Volume (1)
Is part of the Bibliography
- yes (22) (remove)
Keywords
- social media (22) (remove)
Analysis of social media using digital methods is a flourishing approach. However, the relatively easy availability of data collected via platform application programming interfaces has arguably led to the predominance of single-platform research of social media. Such research has also privileged the role of text in social media analysis, as a form of data that is more readily gathered and searchable than images. In this paper, we challenge both of these prevailing forms of social media research by outlining a methodology for visual cross-platform analysis (VCPA), defined as the study of still and moving images across two or more social media platforms. Our argument contains three steps. First, we argue that cross-platform analysis addresses a gap in research methods in that it acknowledges the interplay between a social phenomenon under investigation and the medium within which it is being researched, thus illuminating the different affordances and cultures of web platforms. Second, we build on the literature on multimodal communication and platform vernacular to provide a rationale for incorporating the visual into cross-platform analysis. Third, we reflect on an experimental cross-platform analysis of images within social media posts (n = 471,033) used to communicate climate change to advance different modes of macro- and meso-levels of analysis that are natively visual: image-text networks, image plots and composite images. We conclude by assessing the research pathways opened up by VCPA, delineating potential contributions to empirical research and theory and the potential impact on practitioners of social media communication.
Analysis of social media using digital methods is a flourishing approach. However, the relatively easy availability of data collected via platform application programming interfaces has arguably led to the predominance of single-platform research of social media. Such research has also privileged the role of text in social media analysis, as a form of data that is more readily gathered and searchable than images. In this paper, we challenge both of these prevailing forms of social media research by outlining a methodology for visual cross-platform analysis (VCPA), defined as the study of still and moving images across two or more social media platforms. Our argument contains three steps. First, we argue that cross-platform analysis addresses a gap in research methods in that it acknowledges the interplay between a social phenomenon under investigation and the medium within which it is being researched, thus illuminating the different affordances and cultures of web platforms. Second, we build on the literature on multimodal communication and platform vernacular to provide a rationale for incorporating the visual into cross-platform analysis. Third, we reflect on an experimental cross-platform analysis of images within social media posts (n = 471,033) used to communicate climate change to advance different modes of macro- and meso-levels of analysis that are natively visual: image-text networks, image plots and composite images. We conclude by assessing the research pathways opened up by VCPA, delineating potential contributions to empirical research and theory and the potential impact on practitioners of social media communication.
The immense popularity of online communication services in the last decade has not only upended our lives (with news spreading like wildfire on the Web, presidents announcing their decisions on Twitter, and the outcome of political elections being determined on Facebook) but also dramatically increased the amount of data exchanged on these platforms. Therefore, if we wish to understand the needs of modern society better and want to protect it from new threats, we urgently need more robust, higher-quality natural language processing (NLP) applications that can recognize such necessities and menaces automatically, by analyzing uncensored texts. Unfortunately, most NLP programs today have been created for standard language, as we know it from newspapers, or, in the best case, adapted to the specifics of English social media.
This thesis reduces the existing deficit by entering the new frontier of German online communication and addressing one of its most prolific forms—users’ conversations on Twitter. In particular, it explores the ways and means by how people express their opinions on this service, examines current approaches to automatic mining of these feelings, and proposes novel methods, which outperform state-of-the-art techniques. For this purpose, I introduce a new corpus of German tweets that have been manually annotated with sentiments, their targets and holders, as well as lexical polarity items and their contextual modifiers. Using these data, I explore four major areas of sentiment research: (i) generation of sentiment lexicons, (ii) fine-grained opinion mining, (iii) message-level polarity classification, and (iv) discourse-aware sentiment analysis. In the first task, I compare three popular groups of lexicon generation methods: dictionary-, corpus-, and word-embedding–based ones, finding that dictionary-based systems generally yield better polarity lists than the last two groups. Apart from this, I propose a linear projection algorithm, whose results surpass many existing automatically-generated lexicons. Afterwords, in the second task, I examine two common approaches to automatic prediction of sentiment spans, their sources, and targets: conditional random fields (CRFs) and recurrent neural networks, obtaining higher scores with the former model and improving these results even further by redefining the structure of CRF graphs. When dealing with message-level polarity classification, I juxtapose three major sentiment paradigms: lexicon-, machine-learning–, and deep-learning–based systems, and try to unite the first and last of these method groups by introducing a bidirectional neural network with lexicon-based attention. Finally, in order to make the new classifier aware of microblogs' discourse structure, I let it separately analyze the elementary discourse units of each tweet and infer the overall polarity of a message from the scores of its EDUs with the help of two new approaches: latent-marginalized CRFs and Recursive Dirichlet Process.
Developing a new paradigm
(2020)
Internet users commonly agree that it is important for them to protect their personal data. However, the same users readily disclose their data when requested by an online service. The dichotomy between privacy attitude and actual behaviour is commonly referred to as the “privacy paradox”. Over twenty years of research were not able to provide one comprehensive explanation for the paradox and seems even further from providing actual means to overcome the paradox. We argue that the privacy paradox is not just an instantiation of the attitude-behaviour gap. Instead, we introduce a new paradigm explaining the paradox as the result of attitude-intention and intentionbehaviour gaps. Historically, motivational goal-setting psychologists addressed the issue of intentionbehaviour gaps in terms of the Rubicon Model of Action Phases and argued that commitment and volitional strength are an essential mechanism that fuel intentions and translate them into action. Thus, in this study we address the privacy paradox from a motivational psychological perspective by developing two interventions on Facebook and assess whether the 287 participants of our online experiment actually change their privacy behaviour. The results demonstrate the presence of an intentionbehaviour gap and the efficacy of our interventions in reducing the privacy paradox.
Comment sections of online news platforms are an essential space to express opinions and discuss political topics. However, the misuse by spammers, haters, and trolls raises doubts about whether the benefits justify the costs of the time-consuming content moderation. As a consequence, many platforms limited or even shut down comment sections completely. In this thesis, we present deep learning approaches for comment classification, recommendation, and prediction to foster respectful and engaging online discussions. The main focus is on two kinds of comments: toxic comments, which make readers leave a discussion, and engaging comments, which make readers join a discussion. First, we discourage and remove toxic comments, e.g., insults or threats. To this end, we present a semi-automatic comment moderation process, which is based on fine-grained text classification models and supports moderators. Our experiments demonstrate that data augmentation, transfer learning, and ensemble learning allow training robust classifiers even on small datasets. To establish trust in the machine-learned models, we reveal which input features are decisive for their output with attribution-based explanation methods. Second, we encourage and highlight engaging comments, e.g., serious questions or factual statements. We automatically identify the most engaging comments, so that readers need not scroll through thousands of comments to find them. The model training process builds on upvotes and replies as a measure of reader engagement. We also identify comments that address the article authors or are otherwise relevant to them to support interactions between journalists and their readership. Taking into account the readers' interests, we further provide personalized recommendations of discussions that align with their favored topics or involve frequent co-commenters. Our models outperform multiple baselines and recent related work in experiments on comment datasets from different platforms.
Social Media, Quo Vadis?
(2020)
Over the past two decades, social media have become a crucial and omnipresent cultural and economic phenomenon, which has seen platforms come and go and advance technologically. In this study, we explore the further development of social media regarding interactive technologies, platform development, relationships to news media, the activities of institutional and organizational users, and effects of social media on the individual and the society over the next five to ten years by conducting an international, two-stage Delphi study. Our results show that enhanced interaction on platforms, including virtual and augmented reality, somatosensory sense, and touch- and movement-based navigation are expected. AIs will interact with other social media users. Inactive user profiles will outnumber active ones. Platform providers will diversify into the WWW, e-commerce, edu-tech, fintechs, the automobile industry, and HR. They will change to a freemium business model and put more effort into combating cybercrime. Social media will become the predominant news distributor, but fake news will still be problematic. Firms will spend greater amounts of their budgets on social media advertising, and schools, politicians, and the medical sector will increase their social media engagement. Social media use will increasingly lead to individuals’ psychic issues. Society will benefit from economic growth and new jobs, increased political interest, democratic progress, and education due to social media. However, censorship and the energy consumption of platform operators might rise.
Social Media, Quo Vadis?
(2020)
Over the past two decades, social media have become a crucial and omnipresent cultural and economic phenomenon, which has seen platforms come and go and advance technologically. In this study, we explore the further development of social media regarding interactive technologies, platform development, relationships to news media, the activities of institutional and organizational users, and effects of social media on the individual and the society over the next five to ten years by conducting an international, two-stage Delphi study. Our results show that enhanced interaction on platforms, including virtual and augmented reality, somatosensory sense, and touch- and movement-based navigation are expected. AIs will interact with other social media users. Inactive user profiles will outnumber active ones. Platform providers will diversify into the WWW, e-commerce, edu-tech, fintechs, the automobile industry, and HR. They will change to a freemium business model and put more effort into combating cybercrime. Social media will become the predominant news distributor, but fake news will still be problematic. Firms will spend greater amounts of their budgets on social media advertising, and schools, politicians, and the medical sector will increase their social media engagement. Social media use will increasingly lead to individuals’ psychic issues. Society will benefit from economic growth and new jobs, increased political interest, democratic progress, and education due to social media. However, censorship and the energy consumption of platform operators might rise.
A growing body of research has demonstrated negative effects of sexualization in the media on adolescents' body image, but longitudinal studies and research including interactive and social media are scarce. The current study explored the longitudinal associations of adolescents' use of sexualized video games (SVG) and sexualized Instagram images (SII) with body image concerns. Specifically, our study examined relations between adolescents' SVG and SII use and appearance comparisons, thin- and muscular-ideal internalization, valuing appearance over competence, and body surveillance. A sample of 660 German adolescents (327 female, 333 male;M-age = 15.09 years) participated in two waves with an interval of 6 months. A structural equation model showed that SVG and SII use at Time 1 predicted body surveillance indirectly via valuing appearance over competence at Time 2. Furthermore, SVG and SII use indirectly predicted both thin- and muscular-ideal internalization through appearance comparisons at Time 1. In turn, thin-ideal internalization at Time 1 predicted body surveillance indirectly via valuing appearance over competence at Time 2. The results indicate that sexualization in video games and on Instagram can play an important role in increasing body image concerns among adolescents. We discuss the findings with respect to objectification theory and the predictive value of including appearance comparisons in models explaining the relation between sexualized media and self-objectification.
Feminist Solidarities after Modulation produces an intersectional analysis of transnational feminist movements and their contemporary digital frameworks of identity and solidarity. Engaging media theory, critical race theory, and Black feminist theory, as well as contemporary feminist movements, this book argues that digital feminist interventions map themselves onto and make use of the multiplicity and ambiguity of digital spaces to question presentist and fixed notions of the internet as a white space and technologies in general as objective or universal. Understanding these frameworks as colonial constructions of the human, identity is traced to a socio-material condition that emerges with the modernity/colonialism binary. In the colonial moment, race and gender become the reasons for, as well as the effects of, technologies of identification, and thus need to be understood as and through technologies. What Deleuze has called modulation is not a present modality of control, but is placed into a longer genealogy of imperial division, which stands in opposition to feminist, queer, and anti-racist activism that insists on non-modular solidarities across seeming difference. At its heart, Feminist Solidarities after Modulation provides an analysis of contemporary digital feminist solidarities, which not only work at revealing the material histories and affective ""leakages"" of modular governance, but also challenges them to concentrate on forms of political togetherness that exceed a reductive or essentialist understanding of identity, solidarity, and difference.
A growing body of research has demonstrated negative effects of sexualization in the media on adolescents' body image, but longitudinal studies and research including interactive and social media are scarce. The current study explored the longitudinal associations of adolescents' use of sexualized video games (SVG) and sexualized Instagram images (SII) with body image concerns. Specifically, our study examined relations between adolescents' SVG and SII use and appearance comparisons, thin- and muscular-ideal internalization, valuing appearance over competence, and body surveillance. A sample of 660 German adolescents (327 female, 333 male;M-age = 15.09 years) participated in two waves with an interval of 6 months. A structural equation model showed that SVG and SII use at Time 1 predicted body surveillance indirectly via valuing appearance over competence at Time 2. Furthermore, SVG and SII use indirectly predicted both thin- and muscular-ideal internalization through appearance comparisons at Time 1. In turn, thin-ideal internalization at Time 1 predicted body surveillance indirectly via valuing appearance over competence at Time 2. The results indicate that sexualization in video games and on Instagram can play an important role in increasing body image concerns among adolescents. We discuss the findings with respect to objectification theory and the predictive value of including appearance comparisons in models explaining the relation between sexualized media and self-objectification.