Skip to content

README.md

Latest commit

 

History

History
50 lines (35 loc) · 2.31 KB

README.md

File metadata and controls

50 lines (35 loc) · 2.31 KB
Raw

Strategies of Code-switching in Human-Machine Dialogs

This repository contains the implementation and analysis code for the experiments described in our paper:

Strategies of Code-switching in Human-Machine Dialogs Bilingualism: Language and Cognition (2025)

Overview

Our project implements a Map-Task chatbot used to study code-switching in human–machine interactions. It features a client–server architecture:

  • Client: A React-based web application providing the interactive map-task interface for participants.
  • Server: A Python Flask application implementing the chatbot agent logic and handling communication with the client.

In addition, the repository includes an analysis/ directory containing scripts and notebooks for post-processing and analyzing collected data from our experiments.

Paper Link

📄 Published Paper: Geckt D, Fricke M, Wintner S. Strategies of code-switching in human–machine dialogs. Bilingualism: Language and Cognition. Published online 2025:1-15. doi:10.1017/S1366728925100436 If you use this code in your work, please cite our paper:

📄 Read the preprint on arXiv

If you use this code in your work, please cite our paper:

@article{geckt2025strategiescodeswitchinghumanmachinedialogs,
      title={Strategies of code-switching in human-machine dialogs}, 
      author={Geckt, Dean and Fricke, Melinda and Wintner, Shuly},
      journal={Bilingualism: Language and Cognition},
      pages={1--15},
      year={2025},
      publisher={Cambridge University Press},
      doi={10.1017/S1366728925100436},
      url={https://doi.org/10.1017/S1366728925100436}
}

Directory Structure

.
├── client/        # React web application for the Map-Task interface
├── server/        # Python Flask application implementing the chatbot
├── analysis/      # Data post-processing and analysis scripts
└── README.md