Accessibility navigation


Explainable AI for text classification: lessons from a comprehensive evaluation of post hoc methods

Cesarini, M., Malandri, L., Pallucchini, F., Seveso, A. and Xing, F. ORCID: https://orcid.org/0000-0002-5751-3937 (2024) Explainable AI for text classification: lessons from a comprehensive evaluation of post hoc methods. Cognitive Computation, 16 (6). pp. 3077-3095. ISSN 1866-9964

[thumbnail of Open Access]
Preview
Text (Open Access) - Published Version
· Available under License Creative Commons Attribution.
· Please see our End User Agreement before downloading.

865kB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1007/s12559-024-10325-w

Abstract/Summary

This paper addresses the notable gap in evaluating eXplainable Artificial Intelligence (XAI) methods for text classification. While existing frameworks focus on assessing XAI in areas such as recommender systems and visual analytics, a comprehensive evaluation is missing. Our study surveys and categorises recent post hoc XAI methods according to their scope of explanation and output format. We then conduct a systematic evaluation, assessing the effectiveness of these methods across varying scopes and levels of output granularity using a combination of objective metrics and user studies. Key findings reveal that feature-based explanations exhibit higher fidelity than rule-based ones. While global explanations are perceived as more satisfying and trustworthy, they are less practical than local explanations. These insights enhance understanding of XAI in text classification and offer valuable guidance for developing effective XAI systems, enabling users to evaluate each explainer’s pros and cons and select the most suitable one for their needs.

Item Type:Article
Refereed:Yes
Divisions:Henley Business School > Digitalisation, Marketing and Entrepreneurship
ID Code:123575
Publisher:Springer

Downloads

Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation