sentiment-analysis
Filtering by topic sentiment-analysis(2)Clear all filters
- PaperarXiv — Language & NLP (cs.CL)13 Jul 2026
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
Esteban U. Vega Barajas
A validated protocol for classifying teaching-evaluation comments by category and sentiment was tested for durability and cross-language transfer. Using Spanish and English corpora, the study compared sparse lexical features, frozen transformer embeddings, and prompted LLMs, finding the protocol durable: a 2026 frontier model achieved the highest thematic F1 on Spanish but showed no sentiment advantage over cheaper models, and English sentiment performance was descriptively similar across models. Results indicate that model choice for this task is a deployment decision rather than a property of the protocol.
Original abstract
Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design. Two questions limit its reuse: whether a protocol fixed to 2019-era frozen embeddings stays competitive as representation methods advance, and whether it transfers to a second language. We re-run it on the original Spanish data across three representation generations, sparse lexical features, frozen transformer embeddings, and prompted large language models, and transfer its sentiment task to English with a balanced 45,000-comment corpus checked against an aspect-labeled education dataset. Treating paired comparisons as descriptive, we find the protocol durable: a 2026 frontier model posts the highest thematic F1 on the hardest Spanish task, yet shows no sentiment advantage over a cheap model and no descriptive separation from it on English, so model choice is a deployment decision, not a property of the method.
- PaperLanguage Learning & Technology1 Jan 2026
Sentiment analysis in virtual exchange: Comparing lingua franca and L1-L2 synchronous interactions
Margarita Vinagre, Marta Giralt, Ciara Wigham
The study applied sentiment analysis to oral interactions in synchronous virtual exchanges, comparing groups using English as a lingua franca and those using both L1 and L2. It found that the L1-L2 group showed higher positive emotion and social cognitive processes despite lower L2 proficiency, suggesting bilingual interaction enhances socio-emotional outcomes.
Original abstract
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.