Sentiment analysis in virtual exchange: Comparing lingua franca and L1-L2 synchronous interactions

This study aims to contribute to the growing body of literature examining the socio-emotional and cognitive trajectories of participants in Virtual Exchange (VE). While sentiment analysis has been applied to asynchronous VE interactions and post-exchange written data, its use in analyzing oral interactions within synchronous VE settings remains limited. This research analyzes data from a VE in which Spanish, French, and Irish undergraduates collaborated via videoconferencing. Student dyads interacted using either English as a lingua franca (Spain-France) or bilingually in English and Spanish (Spain-Ireland), and the study examines differences in socio-emotional responses between the two groups. Using LIWC (Linguistic Enquiry Word Count) and supported by content-based qualitative analysis, findings revealed significant increases in word count, positive emotion, affect, and social processes, alongside reductions in negative emotion and anxiety between initial and final interactions. Notably, Group 2 (the L1-L2 group), despite having students with lower proficiency levels in the target language, showed higher results in positive emotion, social, and cognitive processes. This occurred even though they produced fewer words in the L2, highlighting the potential of employing both the L1 and L2 to enhance socio-emotional outcomes in VE.