Deliverables

Review and Guidelines

Review

Systematic review resulting in two complementary outputs: 

  • The first, more theoretical and methodological in nature, consisted in journal article examining the technological and pedagogical affordances of AI-powered chatbots for practicing conversation in English, taking into account the transformative impact of LLMs on the field.
  • The second, more applied, consisted in an inventory of tools for empirical investigation in subsequent project phases. This involved analysing key features such as the naturalness of interaction, the range of language tasks supported, the provision (or lack) of feedback on learners’ English, and the main limitations of the systems. 

 

Literature- and web-based systematic review of available technologies

Polizzi, D., A. Ferraresi, S. Bernardini, C. Cervini, M. Miličević Petrović, and G. Palmieri. Forthcoming. “Re-Evaluating AI Chatbot Effectiveness: A Systematic Review of Dialogue-Based CALL Research.” ALLiED: Journal of Applied Linguistics and Languages in Educational and Digital Settings. 

Link: https://serena.sharepress.it/AL/article/view/13677/13705 

Guidelines

A set of Guidelines for the evaluation of dialogue systems, jointly developed with CAST and grounded in the principles of Universal Design for Learning (UDL). These Guidelines provide a structured and operational framework to assess DS in terms of engagement, representation, and action and expression, with particular attention to the needs of students with disabilities and specific learning disorders. 

 

Chatbot Accessibility Guidelines

Raffi, F., and L. Fedeli. 2026. Chatbot Accessibility Guidelines - Chatbot accessibility assessment within the Universal Design for Learning. Zenodo.
Link: https://doi.org/10.5281/zenodo.18184801

Corpus

Corpus

A richly annotated corpus of written interactions between learners and DS, to support subsequent corpus-based analyses and to provide a reusable resource for the research community. The resulting dataset represents an innovative contribution, as one of the first learner corpora specifically dedicated to human–machine interaction in EFL contexts.

Protocols

Protocols are available here: 

Link: https://doi.org/10.5281/zenodo.19049030

 

UNITE Zenodo Community: 

Link: https://zenodo.org/communities/unite/

 

Open Dataset

On CLARIN infrastructure
Link: http://hdl.handle.net/20.500.11752/OPEN-2156

Tagsets

Tagsets

The UNITE Adaptation of the Louvain Error Tagging System


An adaptation of the Louvain error tagging taxonomy (Granger et al. 2022) within the UNITE project. The original taxonomy, which includes 54 error categories, was extended to address the specific characteristics of the UNITE corpus (Ferraresi et al. 2026), consisting of learner interactions with AI chatbots.

The tagset was released as part of the UNITE corpus package

Link: https://bellatrix.sslmit.unibo.it/noske/public/#dashboard?corpname=unite_corpus

DIS-TAG Tagset

UNIOR unit developed and implemented an innovative annotation framework (DIS-TAG), designed to detect and categorise discursive features related to implicit assumptions about users’ abilities. The annotation revealed recurrent patterns in chatbot language, such as highly standardised politeness, consistent positive reinforcement, and uniformly confident responses, alongside implicit assumptions related to mobility, sensory perception, and cognition.

While not overtly exclusionary, these patterns reflect underlying normative frameworks that may not fully account for user diversity. Importantly, these findings contrast with users’ perceptions of DS as neutral and reliable, highlighting the need to foster critical AI literacy. This strand resulted in the release of both the annotated corpus and the DIS-TAG tagset, which constitutes a novel, reusable resource for the analysis of inclusivity in AI-generated discourse.

Teaching Materials

Teaching Materials

Teaching materials to support the effective and inclusive integration of DS in English as a Foreign Language (EFL) teaching and learning, both in classroom settings and for autonomous learning.

 

  • Intended for "teachers working in classroom settings” but they “can also be used by students engaged in self-directed learning”
  • With the aim to "promote a productive, effective, and informed use of chatbots as conversational partners in the context of English as a second or foreign language (L2) at university level”
  • Recommendations based on corpus evidence

 

Guidelines and teaching materials on the use of DS as tools to practice English

 

Miličević Petrović, M., Cervini, C., Paone, E., Palmieri, G., & Ferraresi, A. (2026). Chatting with Chatbots in L2 English: The UNITE Guidelines. Zenodo.


Link: https://doi.org/10.5281/zenodo.19169244 



Publications

Literature- and web-based systematic review of available technologies

Polizzi, D., A. Ferraresi, S. Bernardini, C. Cervini, M. Miličević Petrović, and G. Palmieri. Forthcoming. “Re-Evaluating AI Chatbot Effectiveness: A Systematic Review of Dialogue-Based CALL Research.” ALLiED: Journal of Applied Linguistics and Languages in Educational and Digital Settings.

Link: https://serena.sharepress.it/AL/article/view/13677/13705

Chatbot Accessibility Guidelines

Raffi, F., and L. Fedeli. 2026. Chatbot Accessibility Guidelines - Chatbot accessibility assessment within the Universal Design for Learning. Zenodo.

Developed in collaboration with: CAST - Until learning has no limits 

Link: https://doi.org/10.5281/zenodo.18184801 

Analysis of students’ attitudes towards DS as a tool to learn and practice English

Fedeli, L., and F. Raffi. 2025. “Digital Innovation in English Language Teaching: The Role of AI Chatbots for Social Sustainability.” The Journal of Language and Teaching Technology 7: 35–45. New Brunswick, NJ: Rutgers University. 

Link: https://hdl.handle.net/11393/367830

Journal special issue on AI and foreign language learning

Ferraresi, A., A. Mongibello, F. Raffi, and S. Bibauw, eds. Forthcoming. “AI and Foreign Language Learning: Bridging Classroom Practice and Research”. Special issue of journal ALLiED: Journal of Applied Linguistics and Languages in Educational Digital Settings. 

Link: https://doi.org/10.6093/al.vi2.13676

Guidelines and teaching materials on the use of DS as tools to practice English

Miličević Petrović, M., Cervini, C., Paone, E., Palmieri, G., & Ferraresi, A. (2026). Chatting with Chatbots in L2 English: The UNITE Guidelines. Zenodo.

Link: https://doi.org/10.5281/zenodo.19169244

Experimental Protocols

Experimental Protocols

The initial phase of the project (M1–M9) was devoted to the overview of available DS and to the preparation of experimental protocols. This phase required more time than originally anticipated, due to the need to reorient the technological focus from “traditional” chatbots to LLM-based systems, which had become dominant shortly before the start of the project. During this phase, UNIBO concentrated on experimentation with emerging tools, while UNIMC focused on refining the inclusivity framework and validating data collection instruments.

Assembling empirical evidence of how Italian university students interact with DS

  • Experimental sessions integrated into English language classes, in collaboration with course lecturers (thanks to CLA Romagna!)
  • Sessions framed as classroom activities in which students were invited to experiment with English-language interaction through DS
  • At UNIBO data collected as part of BAs in (mostly) Political Science, Nursing and Engineering in Forlì, Cesena and Faenza
  • Total number of experimental sessions: 28, of which: 13 at UNIBO; 8 at UNIMC; 7 at UNIOR
  • Data collected: > 400 interactions

Protocols

Protocols available here: 

Link: https://doi.org/10.5281/zenodo.19049030