Description:	Database includes the trained models for the M-Path: https://github.com/onyalcin/M-PATH Likert model is a fine-tuned language model based on BERT, using PyTorch. The model is intended to assign a sentiment classification (negative-positive-neutral) to free-form text input answering survey questions with a 5-level likert scale measurement of frequency. The model is used in M-PATH system, An Empathic Embodied Conversational Agent, published in Github -- the Github repository includes the empathic dialogue management system for an embodied conversational agent, which is created at iVizLab, at Simon Fraser University.
Authors:	Yalçın, Özge Nilay; Simon Fraser University; University of British Columbia; 0000-0002-8898-0466
Keywords:	empathy artificial intelligence conversational agents interactive agents cognitive science machine learning models
Field of Research:	Computer and information sciences > Artificial intelligence (AI) > Cognitive computing Computer and information sciences > Artificial intelligence (AI) > Machine learning
Publication Date:	2022-01-11
Publisher:	Federated Research Data Repository / dépôt fédéré de données de recherche
Funder:	Natural Sciences and Engineering Research Council of Canada (NSERC); RGPIN-2019-06767
URI:	https://doi.org/10.20383/102.0534
Related Identifiers:	This dataset is cited by https://doi.org/10.1007/978-3-030-25719-4_78 This dataset is part/subset of https://github.com/onyalcin/M-PATH
Appears in Collections:	SFU Research Data