ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the use of the toolkit on these datasets.

Emotional Dialogue Acts corpus contains dialogue act labels for the multimodal conversational emotion datasets IEMOCAP and MELD. https://www.aclweb.org/anthology/2020.lrec-1.78/

Context-based Dialogue Act Recognition using Recurrent Neural Networks

this forked repo contains useful datasets

Notes for CL2 course @ IIIT-H

This repository showcases an interactive conversational analysis of the Cornell Movie-Dialogs Corpus, visualised using D3.js, as part of the Data Analysis & Visualisation (DS3001) course final project, encompassing 220,579 exchanges between 10,292 character pairs in 617 movies.

Extracting Emotion-Cause Pairs from Conversations: A Two-Step Approach Using Emotion Classification and QA Models