Using Social Media Data to Analyse Issue Engagement During the 2017 German Federal Election

A fundamental tenet of democracy is that political parties present policy alternatives, such that the public can participate in the decision-making process. Parties, however, strategically control public discussion by emphasising topics that they believe will highlight their strengths in voters’ minds. Political strategy has been studied for decades, mostly by manually annotating and analysing party statements, press coverage, or TV ads. Here we build on recent work in the areas of computational social science and eDemocracy, which studied these concepts computationally with social media. We operationalize issue engagement and related political science theories to measure and quantify politicians’ communication behavior using more than 366k Tweets posted by over 1,000 prominent German politicians in the 2017 election year. To this end, we first identify issues in posted Tweets by utilising a hashtag-based approach well known in the literature. This method allows several prominent issues featuring in the political debate on Twitter that year to be identified. We show that different political parties engage to a larger or lesser extent with these issues. The findings reveal differing social media strategies by parties located at different sides of the political left-right scale, in terms of which issues they engage with, how confrontational they are and how their strategies evolve in the lead-up to the election. Whereas previous work has analysed the general public’s use of Twitter or politicians’ communication in terms of cross-party polarisation, this is the first study of political science theories, relating to issue engagement, using politicians’ social media data.

The Computational Thematic Analysis Toolkit

As online communities have grown, Computational Social Science has rapidly developed new techniques to study them. However, these techniques require researchers to become experts in a wide variety of tools in addition to qualitative and computational research methods. Studying online communities also requires researchers to constantly navigate highly contextual ethical and transparency considerations when engaging with data, such as respecting their members' privacy when discussing sensitive or stigmatized topics. To overcome these challenges, we developed the Computational Thematic Analysis Toolkit, a modular software package that supports analysis of online communities by combining aspects of reflexive thematic analysis with computational techniques. Our toolkit demonstrates how common analysis tasks like data collection, cleaning and filtering, modelling and sampling, and coding can be implemented within a single visual interface, and how that interface can encourage researchers to manage ethical and transparency considerations throughout their research process.

Cognitive cascades: How to model (and potentially counter) the spread of fake news

Understanding the spread of false or dangerous beliefs—often called misinformation or disinformation—through a population has never seemed so urgent. Network science researchers have often taken a page from epidemiologists, and modeled the spread of false beliefs as similar to how a disease spreads through a social network. However, absent from those disease-inspired models is an internal model of an individual’s set of current beliefs, where cognitive science has increasingly documented how the interaction between mental models and incoming messages seems to be crucially important for their adoption or rejection. Some computational social science modelers analyze agent-based models where individuals do have simulated cognition, but they often lack the strengths of network science, namely in empirically-driven network structures. We introduce a cognitive cascade model that combines a network science belief cascade approach with an internal cognitive model of the individual agents as in opinion diffusion models as a public opinion diffusion (POD) model, adding media institutions as agents which begin opinion cascades. We show that the model, even with a very simplistic belief function to capture cognitive effects cited in disinformation study (dissonance and exposure), adds expressive power over existing cascade models. We conduct an analysis of the cognitive cascade model with our simple cognitive function across various graph topologies and institutional messaging patterns. We argue from our results that population-level aggregate outcomes of the model qualitatively match what has been reported in COVID-related public opinion polls, and that the model dynamics lend insights as to how to address the spread of problematic beliefs. The overall model sets up a framework with which social science misinformation researchers and computational opinion diffusion modelers can join forces to understand, and hopefully learn how to best counter, the spread of disinformation and “alternative facts.”

Is Digital Scholarship Meaningful?: A Campus Study Tracking Multidisciplinary Perceptions

Increased computational and multimodal approaches to research over the past decades have enabled scholars and learners to forge creative avenues of inquiry, adopt new methodological approaches, and interrogate information in innovative ways. As such, academic libraries have begun to offer a suite of services to support these digitally inflected and data-intense research strategies. These supports, dubbed digital scholarship services in the library profession, break traditional disciplinary boundaries and highlight the methodological significance of research inquiry. Externally, however, these practices appear as domain-specific niches, e.g., digital history or digital humanities in humanities disciplines, e-science and e-research in STEM, and e-social science or computational social science in social science disciplines. The authors conducted a study examining the meaningfulness of the term digital scholarship within the local context at University of Colorado Boulder by investigating how the interpretation of digital scholarship varies according to graduate students, faculty, and other researchers. Nearly half of the definitions (46 percent) mentioned research process or methods as part of digital scholarship. Faculty and staff declined or were unable to define digital scholarship more often than graduate students or post-doctoral researchers. Therefore, digital scholarship as a term is not meaningful to all researchers. We recommend that librarians inflect their practices with the understanding that researchers and library users’ perceptions of digital scholarship vary greatly across contexts.

The (real) need for a human touch: testing a human–machine hybrid topic classification workflow on a New York Times corpus

The classification of the items of ever-increasing textual databases has become an important goal for a number of research groups active in the field of computational social science. Due to the increased amount of text data there is a growing number of use-cases where the initial effort of human classifiers was successfully augmented using supervised machine learning (SML). In this paper, we investigate such a hybrid workflow solution classifying the lead paragraphs of New York Times front-page articles from 1996 to 2006 according to policy topic categories (such as education or defense) of the Comparative Agendas Project (CAP). The SML classification is conducted in multiple rounds and, within each round, we run the SML algorithm on n samples and n times if the given algorithm is non-deterministic (e.g., SVM). If all the SML predictions point towards a single label for a document, then it is classified as such (this approach is also called a “voting ensemble"). In the second step, we explore several scenarios, ranging from using the SML ensemble without human validation to incorporating active learning. Using these scenarios, we can quantify the gains from the various workflow versions. We find that using human coding and validation combined with an ensemble SML hybrid approach can reduce the need for human coding while maintaining very high precision rates and offering a modest to a good level of recall. The modularity of this hybrid workflow allows for various setups to address the idiosyncratic resource bottlenecks that a large-scale text classification project might face.

Computational Communication Science: Lessons from Working Group Sessions with Experts of an Emerging Research Field

This chapter provides an overview of computational communication science (CCS) as an emerging and exemplary subfield of computational social science. Based on lessons from working group sessions with 34 experts, we address recent challenges and desiderata of CCS research while reflecting upon its future development and expansion. Four major fields of action proved particularly relevant in these discussions: First, challenges related to a reflected but integrated CCS methodology; second, challenges related to a further elaboration on the theoretical perspectives on CCS; third, challenges related to the formation and further institutionalization of CCS as fundamental basis for further scientific exchange, progress and standardization; and fourth, implications for empirical communication research, particularly highlighting the relevance of wicked problems as research incubators driving further progress.

Public Reaction to Scientific Research via Twitter Sentiment Prediction

Purpose Social media users share their ideas, thoughts, and emotions with other users. However, it is not clear how online users would respond to new research outcomes. This study aims to predict the nature of the emotions expressed by Twitter users toward scientific publications. Additionally, we investigate what features of the research articles help in such prediction. Identifying the sentiments of research articles on social media will help scientists gauge a new societal impact of their research articles. Design/methodology/approach Several tools are used for sentiment analysis, so we applied five sentiment analysis tools to check which are suitable for capturing a tweet's sentiment value and decided to use NLTK VADER and TextBlob. We segregated the sentiment value into negative, positive, and neutral. We measure the mean and median of tweets’ sentiment value for research articles with more than one tweet. We next built machine learning models to predict the sentiments of tweets related to scientific publications and investigated the essential features that controlled the prediction models. Findings We found that the most important feature in all the models was the sentiment of the research article title followed by the author count. We observed that the tree-based models performed better than other classification models, with Random Forest achieving 89% accuracy for binary classification and 73% accuracy for three-label classification. Research limitations In this research, we used state-of-the-art sentiment analysis libraries. However, these libraries might vary at times in their sentiment prediction behavior. Tweet sentiment may be influenced by a multitude of circumstances and is not always immediately tied to the paper's details. In the future, we intend to broaden the scope of our research by employing word2vec models. Practical implications Many studies have focused on understanding the impact of science on scientists or how science communicators can improve their outcomes. Research in this area has relied on fewer and more limited measures, such as citations and user studies with small datasets. There is currently a critical need to find novel methods to quantify and evaluate the broader impact of research. This study will help scientists better comprehend the emotional impact of their work. Additionally, the value of understanding the public's interest and reactions helps science communicators identify effective ways to engage with the public and build positive connections between scientific communities and the public. Originality/value This study will extend work on public engagement with science, sociology of science, and computational social science. It will enable researchers to identify areas in which there is a gap between public and expert understanding and provide strategies by which this gap can be bridged.

Scaling up experimental social, behavioral, and economic science

The standard experimental paradigm in the social, behavioral, and economic sciences is extremely limited. Although recent advances in digital technologies and crowdsourcing services allow individual experiments to be deployed and run faster than in traditional physical labs, a majority of experiments still focus on one-off results that do not generalize easily to real-world contexts or even to other variations of the same experiment. As a result, there exist few universally acknowledged findings, and even those are occasionally overturned by new data. We argue that to achieve replicable, generalizable, scalable and ultimately useful social and behavioral science, a fundamental rethinking of the model of virtual-laboratory style experiments is required. Not only is it possible to design and run experiments that are radically different in scale and scope than was possible in an era of physical labs; this ability allows us to ask fundamentally different types of questions than have been asked historically of lab studies. We posit, however, that taking full advantage of this new and exciting potential will require four major changes to the infrastructure, methodology, and culture of experimental science: (1) significant investments in software design and participant recruitment, (2) innovations in experimental design and analysis of experimental data, (3) adoption of new models of collaboration, and (4) a new understanding of the nature and role of theory in experimental social and behavioral science. We conclude that the path we outline, although ambitious, is well within the power of current technology and has the potential to facilitate a new class of scientific advances in social, behavioral and economic studies.This paper emerged from discussions at a workshop held by the Computational Social Science Lab at the University of Pennsylvania in January 2020. The work was supported by James and Jane Manzi Analytics Fund and the Alfred P. Sloan Foundation.