Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code-mixing as Cues

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 1490–1495 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 1490 Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code- mixing as Cues Xinyuan Xia, Lu Xiao, Kun Yang, Yueyue Wang Department of Languages, Literatures, and Linguistics, School of Information Studies, College of Arts and Science, Syracuse University {xxia16, lxiao04, kyang23, ywang153}@syr.edu Abstract In this study, we thrive on finding out how code-switching and code-mixing (CS/CM) as a linguistic phenomenon could be a sign of tension in Holocaust survivors' interviews. We first created an interview corpus (a total of 39 interviews) that contains manually annotated CS/CM codes (a total of 802 quotations). We then compared our annotations with the tension places in the corpus. The tensions are identified by a computational tool. We found that most of our annotations were captured in the tension places, and it showed a relatively outstanding performance. The finding implies that CS/CM can be appropriate cues for detecting tension in this communication context. Our CS/CM annotated interview corpus is openly accessible. Aside from annotating and examining CS/CM occurrences, we annotated silence situations in this open corpus, as it is shown to be an indicator of tension in interpersonal communications in previous research. Making this corpus openly accessible, we call for more research endeavors on tension detection. Keywords: Code-switching, Code-mixing, Silence, Tension, Holocaust Interviews 1. Introduction “Tension” is defined as “inner striving, unrest, or imbalance often with the physiological indicators of emotion,” or “a state of latent hostility or opposition between individuals or groups” on Merriam-Webster dictionary. Therefore, when it comes to tension, it always revolves around feelings and emotions. The state of tension could be affected by psychological, phonological, and morphological aspects. In interpersonal communications, people sometimes feel uncomfortable responding to a question or discussing a topic brought up by their conversation partner, who, on the other hand, is eager to explore. They may tolerate the situation, and their responses do not reveal their discomfort. Or they may use various strategies in their responses consciously or subconsciously, such as responding in silence or switching the topic. In the second case, internally, this discomfort experienced by the people may be identified based on how they communicate and what they communicate. We call such situations in communication the tension states. Depending on the communication context, the flow can be negatively affected when tension occurs, and the communication goal may not be achieved (Sins & Karlgren, 2009). With more and more communication data available in electronic form, researchers explore computational approaches that automatically identify tensions from such data (Islam, Mercer, Xiao, & High, 2019), and tension analysis in the data is getting research attention (e.g., Burnap et al., 2015). This study is particularly interested in identifying and analyzing tensions in survivor or witness interviews about mass violence. It is expected that tensions will occur in these Holocaust survivors’ interviews. Specifically, these personal stories and testimonies about mass violence are often explored through life …

Content truncated to 500 words