ABSTRACT Communication is commonly considered a process that is dynamically situated in a temporal context. However, there remains a disconnection between this theoretical dynamicality and the often less dynamic methods that communication scholars use to study it. Given the increasing accessibility of digital trace data, this study provides a methodological overview of how such fine-grained temporal information can be used in communication research. In particular, we show how to retain the hyper-longitudinal information in the trace data and analyze time-evolving “user-sequences,” which capture user activities at high temporal resolution. We then survey a set of established sequential methods, including sequence analysis, event history analysis, hidden Markov models, network analysis, process mining, and language-based models. We also articulate important sequential features that can be studied within user-sequences, such as transitions, subsequences, and trajectories. As an illustrative example, we apply the six methods to real-world user-sequences containing 1,262,775 timestamped traces from 309 unique users, gathered via data donations. Overall, our study provides a methodological overview of sequence analysis applied to digital trace data and offers initial guidance on method selection.

ABSTRACT As the exploration of digital behavioral data revolutionizes communication research, understanding the nuances of data collection methodologies becomes increasingly pertinent. This study focuses on one prominent data collection approach, web scraping;specifically, its application in the growing field of research relying on web browsing data. We investigate discrepancies between content obtained directly during user interaction with a website (in-situ) and content scraped using the URLs of participants’ logged visits (ex-situ) with various time delays (0, 30, 60, and 90 days). We find substantial disparities between the methodologies, uncovering that errors are not uniformly distributed across news categories regardless of the classification method (domain, URL, or content analysis). These biases compromise the precision of measurements used in the existing literature. The ex-situ collection environment is the primary source of the discrepancies (~33.8%), while the time delays in the scraping process play a smaller role (adding ~6.5% points in 90 days). Our research emphasizes the need for data collection methods that capture web content directly in the user’s environment. However, acknowledging its complexities, we further explore strategies to mitigate biases in web-scraped browsing histories, offering recommendations for researchers who rely on this method and laying the groundwork for developing error-correction frameworks.

ABSTRACT This paper demonstrates the performance of the Joint Sentiment Topic model (JST) and the reversed Joint Sentiment Topic model (rJST) in measuring sentiment in political speeches, comparing them against a set of popular methods for sentiment analysis: widely used off-the-shelf sentiment dictionaries; an embeddings-enhanced dictionary approach; Latent Semantic Scaling, a semi-supervised approach; and a zero-shot transformer-based approach using a large language model (GPT-4). The findings reveal JST’s superiority over all non-transformer-based approaches in predicting human-coded sentiment in multiple languages and its ability to replicate known sentiment trends in legislative speech. rJST, meanwhile, provides valuable topic-specific sentiment estimates, responsive to political dynamics and significant events. Both models are, however, outperformed by transformer-based models like GPT-4. Additionally, the paper introduces the ’sentitopics’ R-package, designed to facilitate the use of JST and rJST in computational text analysis workflows. This package is compatible with popular text analysis tools, making the models accessible for applied researchers in communication science.

ABSTRACT Named Entity Recognition (NER) is a supervised machine learning task that finds various applications in automated content analysis, as the identification of entities is vital for understanding public discourse. However, sometimes the standard NER labels are not specific enough for a given domain. We introduce Public Entity Recognition (PER). PER is a domain-specific version of NER, that is trained for five entity types that are common to public discourse: politicians, parties, authorities, media, and journalists. PER can be used for pre-processing documents, in a pipeline with other classifiers or directly for analyzing information in texts. The taxonomy for PER is taken from the database of (German) public speakers and aims at low-threshold integration into computational social science research. We experiment with different training settings, involving weakly supervised training and training on manually annotated data. We evaluate multilingual transformer models of different sizes against rule-based entity matching and find that the models do not only outperform the baseline but also reach competitive absolute scores of around .8 and higher in F1. We further test for generalization and domain adaptation. We show that with only around 100–150 additional sentences, the model can be adapted to new languages.

ABSTRACT Topic Modelling has established itself as one of the major text-as-data methodologies within the social sciences in general, and in communications science, in particular. The core strength of TM approaches is the fact that it is essentially a 2-in-1 method, as it both generates clusters into which the texts may fall as well as classifies the texts according to the clusters. Previous research has pointed out that pre-processing text corpora is as much a part of text analysis as the latter stages. Named Entity Recognition, however, is not often thought of when pre-processing texts for analysis and has thus far not received much attention in relation to the TM pipeline. If simply retaining or removing stop words can produce different interpretations of the outcomes of TM, retaining or removing NEs also has consequences on outcomes and interpretations. The current paper analyses the effects that removing/retaining NEs has on the interpretability of topic models. Both model statistics and human validation are used to address this issue. The results show differences in topics models trained on corpora with and without NEs. TMs trained on corpora where NEs are removed exhibit different structural characteristics, and, more importantly, are perceived differently by human coders. We attempt to formulate recommendations regarding the pre-processing of NEs in TM applications.

ABSTRACT Understanding the implications of aggressive political debate style amid corrosive modes of campaign politics requires fine-grained analyses of political performance, attending to multiple communication modalities. Politicians’ facial expressions, emotional tone, and speech content can all independently convey aggression and dominance, and often work in combination for purposes of emphasis. Yet micro-coding individual visual, tonal, and verbal features across more than a handful of debate segments becomes extremely labor intensive, hampering research, especially historical, longitudinal, and cross-cultural work. To address this limitation, we develop a novel multimodal classifier using an Interaction Canonical Correlation Network (ICCN) that incorporates video and audio features with speech coding of candidate debate performance, trained on a 20% sample of 10-second segments from each of the first televised U.S presidential debates between 1980 and 2020. In the analysis, we demonstrate this classifier can accurately detect aggression by political candidates in U.S. debates. We sharpen its performance by distinguishing between debate eras characterized by lower and higher levels of aggression and validate the approach by comparing the performance of unimodal with multimodal classification. This classifier opens new avenues for computational social science research, including explaining candidate behavior within debates at a larger scale and across different eras.

ABSTRACT Using data donations to collect digital trace data holds great potential for communication research, which has not yet been fully realized. Besides limited awareness and expertise among researchers, a central challenge is to motivate people to donate their personal data. Therefore, this article investigates which factors affect people’s willingness to donate across different platforms and data types. The study applies a multilevel approach that explains the reported willingness to donate different types of data (level 1) belonging to different platforms (level 2) from potential data donors with individual characteristics (level 3) to a hypothetical research project. The analysis is based on data collected through a national online survey (n = 833). We find higher willingness to donate YouTube data compared to Facebook, Instagram, or Google, as well as relevant influencing factors at all three levels. Greater willingness is found for lower perceived sensitivity and higher perceived relevance of the data (level of data type), greater perceived behavioral control to request and submit the data (platform level), more favorable attitudes toward data donation and the donation purpose, as well as lower contextual privacy concerns (individual level). Based on these findings, practical implications for future data donation studies are proposed.

ABSTRACT Studies assessing the effects of social media use are largely based on measures of time spent on social media. In recent years, scholars increasingly ask for more insights in social media activities and content people engage with. Data Download Packages (DDPs), the archives of social media platforms that each European user has the right to download, provide a new and promising method to collect timestamped and content-based information about social media use. In this paper, we first detail the experiences and insights of a data collection of 110 Instagram DDPs gathered from 102 adolescents. We successively discuss the challenges and opportunities of collecting and analyzing DDPs to help future researchers in their consideration of whether and how to use DDPs. DDPs provide tremendous opportunities to get insight in the frequency, range, and content of social media activities, from browsing to searching and posting. Yet, collecting, processing, and analyzing DDPs is also complex and laborious, and demands numerous procedural and analytical choices and decisions.

ABSTRACT This paper discusses ‘strong-form’ frequentist testing as a useful complement to null hypothesis testing in communication science. In a ‘strong-form’ set-up a researcher defines a hypothetical effect size of (minimal) theoretical interest and assesses to what extent her findings falsify or corroborate that particular hypothesis. We argue that the idea of ‘strong-form’ testing aligns closely with the ideals of the movements for scientific reform, discuss its technical application within the context of the General Linear Model, and show how the relevant P-value-like quantities can be calculated and interpreted. We also provide examples and a simulation to illustrate how a strong-form set-up requires more nuanced reflections about research findings. In addition, we discuss some pitfalls that might still hold back strong-form tests from widespread adoption.

ABSTRACT Although media and communication scholars have suggested various analytical methods for measuring and comparing news audience polarization across countries, we lack a systematic assessment of the metrics produced by these techniques. Using survey data from the 2016 Reuters Institute Digital News Report on news use in 26 countries, we address this gap through a resampling simulation experiment. Our simulation revealed a strong impact of analytical choices, which invited disparate interpretations in terms of how polarized news audiences are, how strongly audience polarization structurally varies between news environments, and how news audience polarization is distributed cross-nationally. Alternative choices led to profound differences in the compatibility, consistency, and validity of the empirical news audience polarization estimates. We conclude from these results that a more precise methodological understanding of news audience polarization metrics informs our capability to draw meaningful inferences from empirical work.