Chatbots are increasingly attracting the interest of language teachers and language acquisition researchers, in light of their virtually unlimited availability and the wide variety of learning contexts provided. In this paper, we draw on this interest and present work aimed at building a corpus of written interactions between learners and chatbots, focusing specifically on second language (L2) English and students who are native speakers of Italian. Unlike previous studies, primarily interested in motivation and/or the assessment of language skills following interaction with chatbots, we concentrate on the collection and analysis of authentic language produc- tion. We describe the criteria adopted for the selection of chatbots and cor- pus construction and present some initial data. The findings point to chatbots being efficient and approachable conversation partners viewed by learners in a predominantly positive light.
Cervini, C., Milicevic Petrovic, M. (2025). Chiacchiere in inglese: verso la costruzione di un corpus di interazioni tra apprendenti e chatbot. RASSEGNA ITALIANA DI LINGUISTICA APPLICATA, 57(1-2-3), 169-187.
Chiacchiere in inglese: verso la costruzione di un corpus di interazioni tra apprendenti e chatbot
Cristiana Cervini;Maja Milicevic Petrovic
2025
Abstract
Chatbots are increasingly attracting the interest of language teachers and language acquisition researchers, in light of their virtually unlimited availability and the wide variety of learning contexts provided. In this paper, we draw on this interest and present work aimed at building a corpus of written interactions between learners and chatbots, focusing specifically on second language (L2) English and students who are native speakers of Italian. Unlike previous studies, primarily interested in motivation and/or the assessment of language skills following interaction with chatbots, we concentrate on the collection and analysis of authentic language produc- tion. We describe the criteria adopted for the selection of chatbots and cor- pus construction and present some initial data. The findings point to chatbots being efficient and approachable conversation partners viewed by learners in a predominantly positive light.| File | Dimensione | Formato | |
|---|---|---|---|
|
CERVINI_MILICEVIC-PETROVIC_2025.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale / Version Of Record
Licenza:
Licenza per accesso libero gratuito
Dimensione
1.33 MB
Formato
Adobe PDF
|
1.33 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


