While the traditional agenda-setting theory assumes that a unified issue salience pattern (“the agenda”) will transfer from news media to the public, the emergence of the Internet has challenged this classic communication theory in three ways: by providing two versions of the public agenda (i.e., self-reported issue importance measured by a survey versus social media expressions), by affording two versions of the media agenda (i.e., presented on news websites versus on organizations’ Twitter accounts), and by enabling potential two-way agenda-setting effects. This dissertation aims to construct a multi-version two-way agenda-setting framework via (1) elaborating on the theoretical and practical reasons behind the proposed framework and (2) empirically testing the framework by combining survey and digital texts data around the 2020 US presidential election. The results show an imbalanced two-way agenda-setting relationship, with the traditional media-to-public direction still stronger than the reverse. While the two versions of the media agenda were similar to each other, what people thought was found to be different from what they tweeted. This dissertation also explored the moderating effects of issue-, media-, and individual-level characteristics on the direction and strength of the agenda-setting effects. The issue-wise comparison showed stronger effects in both directions among obtrusive issues, compared to non-obtrusive issues. Interestingly, traditional, non-digital-native media presented a slightly stronger two-way agenda-setting relationship between their news tweets and citizens' tweets compared to digital-native media. This difference, however, was not found in news websites. Individuals with specific characteristics, such as being females, being older, being white, as well as having lower income, lower opinion leadership, and lower social capital, were more likely to influence and be influenced by the media agendas compared to their counterparts. Also, while the well-educated population followed the agenda of news websites more closely, the group with a lower education level followed news tweets on more issues. Finally, the last chapter discusses theoretical, methodological, and practical implications.

No description available.

This thesis investigates how group-level differences in willingness of opinion expression shape the extent to which certain standpoints are visible in public debate online. Against the backdrop of facilitated communication and connection to like-minded others through digital technologies, models and methods are developed and case studies are carried out – by and large from a network perspective. To this end, we first propose a model of opinion dynamics that examines social- structural conditions for public opinion expression or even predominance of different groups. The model focuses not on opinion change, but on the decision of individuals whether to express their opinion publicly or not. Groups of agents with different, fixed opinions interact with each other, changing the willingness to express their opinion according to the feedback they receive from others. We formulate the model as a multi-group game, and subsequently provide a dynamical systems perspective by introducing reinforcement learning dynamics. We show that a minority can dominate public discourse if its internal connections are sufficiently dense. Moreover, increased costs for opinion expression can drive even internally well-connected groups into silence. We then focus on how interaction networks can be used to infer political and social positions. For this purpose, we develop a new type of force-directed network layout algorithm. While being widely used, a rigorous interpretation of the outcomes of existing force-directed algorithms has not been provided yet. We argue that interpretability can be delivered by latent space approaches, which have the goal of embedding a network in an underlying social space. On the basis of such a latent space model, we derive a force-directed layout algorithm that can not only be used for the spatialisation of generic network data – exemplified by Twitter follower and retweet networks, as well as Facebook friendship networks – but also for the visualization of surveys. Comparison to existing layout algorithms (which are not grounded in an interpretable model) reveals that node groups are placed in similar configurations, while said algorithms show a stronger intra-cluster separation of nodes, as well as a tendency to separate clusters more strongly in retweet networks. In two case studies, we observe actual public debate on the social media platform Twitter – topics are the Saxon state elections 2019, and violent riots in the city of Leipzig on New Year’s Eve in the same year. We show that through the interplay of retweet and reply networks, it is possible to identify differences in willingness of opinion expression on the platform between opinion groups. We find that for both events, propensities to get involved in debate are asymmetric. Users retweeting far-right parties and politicians are significantly more active, making their positions disproportionately visible. Said users also act significantly more confrontational in the sense that they reply mostly to users from different groups, while the contrary is not the case. The findings underline that naive reliance on what others express online can be collectively dangerous, especially in an era in which social media shapes public discourse to an unprecedented extent.

Social psychology has a long tradition of studying the personality traits associated with subjective well-being (SWB). However, research often depends on a priori but unempirical assumptions about how to (a) measure the constructs, and (b) mitigate confounded associations. These assumptions have caused profligate and often contradictory findings. To remedy, I demonstrate how a computational psychology paradigm-predicated on large online data and iterative analyses-might help isolate more robust personality trait associations. At the outset, I focussed on univariate measurement. In the first set of studies, I evaluated the extent researchers could measure psychological characteristics at scale from online behaviour. Specifically, I used a combination of simulated and real-world data to determine whether predicted constructs like big five personality were accurate for specific individuals. I found that it was usually more effective to simply assume everyone was average for the characteristic, and that imprecision was not remedied by collapsing predicted scores into buckets (e.g. low, medium, high). Overall, I concluded that predictions were unlikely to yield precise individual-level insights, but could still be used to examine normative group-based tendencies. In the second set of studies, I evaluated the construct validity of a novel SWB scale. Specifically, I repurposed the balanced measure of psychological needs (BMPN), which was originally designed to capture the substrates of intrinsic motivation. I found that the BMPN robustly captured (a) dissociable experiences of suffering and flourishing, (b) more transitive SWB than the existing criterion measure, and (c) unique variation in real-world outcomes. Thus, I used it as my primary outcome. Then, I focussed on bivariate associations. The third set of studies extracted pairs of participants with similar patterns of covarying personality traits-and differing target traits-to isolate less-confounded SWB correlations. I found my extraction method-an adapted version of propensity score matching-outperformed even advanced machine learning alternatives. The final set of studies isolated the subset of facets that had the most robust associations with SWB. It combined real-world surveys with a total of eight billion simulated participants to find the traits most prevalent in extreme suffering and flourishing. For validation purposes, I first found that depression and cheerfulness-the trait components of SWB-were highly implicated in both suffering and flourishing. Then, I found that self-discipline was the only other trait implicated in both forms of SWB. However, there were also domain-specific effects: anxiety, vulnerability and cooperation were implicated in just suffering; and, assertiveness, altruism and self-efficacy were implicated in just flourishing. These seven traits were most likely to be the definitive, stable, drivers of SWB because their effects were totally consistent across the full range of intrapersonal contexts.

De nombreux domaines ont intérêt à étudier les points de vue exprimés en ligne, que ce soit à des fins de marketing, de cybersécurité ou de recherche avec l'essor des humanités numériques. Nous proposons dans ce manuscrit deux contributions au domaine de la fouille de points de vue, axées sur la difficulté à obtenir des données annotées de qualité sur les médias sociaux. Notre première contribution est un jeu de données volumineux et complexe de 22853 profils Twitter actifs durant la campagne présidentielle française de 2017. C'est l'un des rares jeux de données considérant plus de deux points de vue et, à notre connaissance, le premier avec un grand nombre de profils et le premier proposant des communautés politiques recouvrantes. Ce jeu de données peut être utilisé tel quel pour étudier les mécanismes de campagne sur Twitter ou pour évaluer des modèles de détection de points de vue ou des outils d'analyse de réseaux. Nous proposons ensuite deux modèles génériques semi-supervisés de détection de points de vue, utilisant une poignée de profils-graines, pour lesquels nous connaissons le point de vue, afin de catégoriser le reste des profils en exploitant différentes proximités inter-profils. En effet, les modèles actuels sont généralement fondés sur les spécificités de certaines plateformes sociales, ce qui ne permet pas l'intégration de la multitude de signaux disponibles. En construisant des proximités à partir de différents types d'éléments disponibles sur les médias sociaux, nous pouvons détecter des profils suffisamment proches pour supposer qu'ils partagent une position similaire sur un sujet donné, quelle que soit la plateforme. Notre premier modèle est un modèle ensembliste séquentiel propageant les points de vue grâce à un graphe multicouche représentant les proximités entre les profils. En utilisant des jeux de données provenant de deux plateformes, nous montrons qu'en combinant plusieurs types de proximité, nous pouvons correctement étiqueter 98% des profils. Notre deuxième modèle nous permet d'observer l'évolution des points de vue des profils pendant un événement, avec seulement un profil-graine par point de vue. Ce modèle confirme qu'une grande majorité de profils ne changent pas de position sur les médias sociaux, ou n'expriment pas leur revirement. / Numerous domains have interests in studying the viewpoints expressed online, be it for marketing, cybersecurity, or research purposes with the rise of computational social sciences. We propose in this manuscript two contributions to the field of stance detection, focused around the difficulty of obtaining annotated data of quality on social medias. Our first contribution is a large and complex dataset of 22853 Twitter profiles active during the French presidential campaign of 2017. This is one of the rare datasets that considers a non-binary stance classification and, to our knowledge, the first one with a large number of profiles, and the first one proposing overlapping political communities. This dataset can be used as-is to study the campaign mechanisms on Twitter, or used to test stance detection models or network analysis tools. We then propose two semi-supervised generic stance detection models using a handful of seed profiles for which we know the stance to classify the rest of the profiles by exploiting various proximities. Indeed, current stance detection models are usually grounded on the specificities of some social platforms, which is unfortunate since it does not allow the integration of the multitude of available signals. By infering proximities from differents types of elements available on social medias, we can detect profiles close enough to assume they share a similar stance on a given subject. Our first model is a sequential ensemble algorithm which propagates stances thanks to a multi-layer graph representing proximities between profiles. Using datasets from two platforms, we show that, by combining several types of proximities, we can achieve excellent results. Our second model allows us to observe the evolution of profiles' stances during an event with as little as one seed profile by stance. This model confirms that a large majority of profiles do not change their stance on social medias, or do not express their change of heart.

abstract: What causes social systems to resist change? Studies of the emergence of social complexity in archaeology have focused primarily on drivers of change with much less emphasis on drivers of stability. Social stability, or the persistence of social systems, is an essential feature without which human society is not possible. By combining quantitative modeling (Exponential Random Graph Modeling) and the comparative archaeological record where the social system is represented by networks of relations between settlements, this research tests several hypotheses about social and geographic drivers of social stability with an explicit focus on a better understanding of contexts and processes that resist change. The Valencian Bronze Age in eastern Spain along the Mediterranean, where prior research appears to indicate little, regional social change for 700 years, serves as a case study. The results suggest that social stability depends on a society’s ability to integrate change and promote interdependency. In part, this ability is constrained or promoted by social structure and the different, relationship dependencies among individuals that lead to a particular social structure. Four elements are important to constraining or promoting social stability—structural cohesion, transitivity and social dependency, geographic isolation, and types of exchange. Through the framework provided in this research, an archaeologist can recognize patterns in the archaeological data that reflect and promote social stability, or lead to collapse. Results based on comparisons between the social networks of the Northern and Southern regions of the Valencian Bronze Age show that the Southern Region’s social structure was less stable through time. The Southern Region’s social structure consisted of competing cores of exchange. This type of competition often leads to power imbalances, conflict, and instability. Strong dependencies on the neighboring Argaric during the Early and Middle Bronze Ages and contributed to the Southern Region’s inability to maintain social stability after the Argaric collapsed. Furthermore, the Southern Region participated in the exchange of more complex technology—bronze. Complex technologies produce networks with hub and spoke structures highly vulnerable to collapse after the destruction of a hub. The Northern Region’s social structure remained structurally cohesive through time, promoting social stability. / Dissertation/Thesis / Webpage with data tables and R code / Doctoral Dissertation Anthropology 2020

abstract: Internet memes have become a widespread tool used by people for interacting and exchanging ideas over social media, blogs, and open messengers. Internet memes most commonly take the form of an image which is a combination of image, text, and humor, making them a powerful tool to deliver information. Image memes are used in viral marketing and mass advertising to propagate any ideas ranging from simple commercials to those that can cause changes and development in the social structures like countering hate speech. This work proposes to treat automatic image meme generation as a translation process, and further present an end to end neural and probabilistic approach to generate an image-based meme for any given sentence using an encoder-decoder architecture. For a given input sentence, a meme is generated by combining a meme template image and a text caption where the meme template image is selected from a set of popular candidates using a selection module and the meme caption is generated by an encoder-decoder model. An encoder is used to map the selected meme template and the input sentence into a meme embedding space and then a decoder is used to decode the meme caption from the meme embedding space. The generated natural language caption is conditioned on the input sentence and the selected meme template. The model learns the dependencies between the meme captions and the meme template images and generates new memes using the learned dependencies. The quality of the generated captions and the generated memes is evaluated through both automated metrics and human evaluation. An experiment is designed to score how well the generated memes can represent popular tweets from Twitter conversations. Experiments on Twitter data show the efficacy of the model in generating memes capable of representing a sentence in online social interaction. / Dissertation/Thesis / Masters Thesis Computer Science 2020

abstract: Millions of users leave digital traces of their political engagements on social media platforms every day. Users form networks of interactions, produce textual content, like and share each others' content. This creates an invaluable opportunity to better understand the political engagements of internet users. In this proposal, I present three algorithmic solutions to three facets of online political networks; namely, detection of communities, antagonisms and the impact of certain types of accounts on political polarization. First, I develop a multi-view community detection algorithm to find politically pure communities. I find that word usage among other content types (i.e. hashtags, URLs) complement user interactions the best in accurately detecting communities. Second, I focus on detecting negative linkages between politically motivated social media users. Major social media platforms do not facilitate their users with built-in negative interaction options. However, many political network analysis tasks rely on not only positive but also negative linkages. Here, I present the SocLSFact framework to detect negative linkages among social media users. It utilizes three pieces of information; sentiment cues of textual interactions, positive interactions, and socially balanced triads. I evaluate the contribution of each three aspects in negative link detection performance on multiple tasks. Third, I propose an experimental setup that quantifies the polarization impact of automated accounts on Twitter retweet networks. I focus on a dataset of tragic Parkland shooting event and its aftermath. I show that when automated accounts are removed from the retweet network the network polarization decrease significantly, while a same number of accounts to the automated accounts are removed randomly the difference is not significant. I also find that prominent predictors of engagement of automatically generated content is not very different than what previous studies point out in general engaging content on social media. Last but not least, I identify accounts which self-disclose their automated nature in their profile by using expressions such as bot, chat-bot, or robot. I find that human engagement to self-disclosing accounts compared to non-disclosing automated accounts is much smaller. This observational finding can motivate further efforts into automated account detection research to prevent their unintended impact. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2019

Web surveys in higher education are particularly important for assessing the quality of academic teaching and learning. Traditionally, mainly quantitative data is used for quality assessment. Increasingly, questions are being raised about the impact of attitudes of the individuals involved. Therefore, especially the analysis of open-ended text responses in web surveys offers the potential for impact evaluation. Despite the fact that qualitative text mining and sentiment analysis are being introduced in other research areas, these instruments are still slowly gaining access to evaluation research. On the one hand, there is a lack of methodological expertise to deal with large numbers of text responses (e.g. via semantic analysis, linguistically supported coding, etc.). On the other hand, deficiencies in interdisciplinary expertise are identified in order to be able to contextualize the results. The following contribution aims to address these issues. The presentation will contribute to the field of impact evaluation and reveals methodological implications for the development of text mining and sentiment analysis in evaluation processes.

Over the last several decades there has been a debate among social scientists on whether the United States has become, or is in the process of being, politically polarized. These conversations started with discussion of the “culture wars,” moved to the discussion of selective exposure and media outrage, and currently involve concerns about online radicalization and the spread of online misinformation. Throughout these themes one characteristic has remained constant: a lack of systematic evidence despite anecdotes and feelings of animosity between the two parties. Today researchers are beginning to shift from operationalizing political polarization as growing divides in attitudes towards policy issues towards a focus on political animosity. Scholars attempting to understand the origins of affective polarization have looked at the effect of political identity, out-group perceptions, and the diffusion of moral and emotional content in social media networks. In the current study I build on this literature using a panel of longitudinal data Twitter users to examine whether there is an association between following prominent partisan Twitter accounts and the expression of emotional valence through Tweeting or Retweeting. I take a relational approach to analysis by examining how this relationship varies between networks of Twitter users and under different historical circumstances. I argue that this relational approach is necessary for understanding how political polarization is unfolding in the country and that the lack of a relational approach may explain why political polarization has been downplayed in systematic studies. This study finds that the amount of political polarization on Twitter is dependent both on cultural and historical context. It makes contributions to the literature on political polarization in the United States, research methodology, and has implications for reducing radicalization in online spaces.