Khallaf, Nouran and Ezeani, Ignatius and Knight, Dawn and Rayson, Paul and El-Haj, Mo and Vidler, John and Davies, James and Alva-Manchego, Fernando (2025) FreeTxt: Analyse and Visualise Multilingual Qualitative Survey Data for Cultural Heritage Sites. In: Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era :. Incoma Ltd. Shoumen, BULGARIA, Varna, Bulgaria, pp. 541-545.
Full text not available from this repository.Abstract
We introduce FreeTxt, a free and open-source web-based tool designed to support the analysis and visualisation of multilingual qualitative survey data, with a focus on low-resource languages. Developed in collaboration with stakeholders, FreeTxt integrates established techniques from corpus linguistics with modern natural language processing methods in an intuitive interface accessible to non-specialists. The tool currently supports bilingual processing and visualisation of English and Welsh responses, with ongoing extensions to other languages such as Vietnamese. Key functionalities include semantic tagging via PyMUSAS, multilingual sentiment analysis, keyword and collocation visualisation, and extractive summarisation. User evaluations with cultural heritage institutions demonstrate the system's utility and potential for broader impact.