Corpus for Emotion Detection on Roman Urdu
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Language assets, like corpora, are essential for different natural language processing tasks. There are many useful applications of emotion analysis of text such as dialog systems, smart agents, mental disorder clinical diagnoses. In this research, an emotion labeled corpus for Roman Urdu is presented for evaluation of emotions in short text. We collected a sizable corpus with 10,000 manually annotated sentences in Roman Scripted Urdu to facilitate the development and evaluation of emotion detection systems for Roman Urdu. This corpus is the first of its kind to be created for the Roman Urdu.Keywords
This publication has 17 references indexed in Scilit:
- Emotion detection in blog posts using keyword spotting and semantic analysis2017
- Urdu Sentiment Analysis Using Supervised Machine Learning ApproachInternational Journal of Pattern Recognition and Artificial Intelligence, 2017
- Automatic emotional spoken language text corpus construction from written dialogs in fictions2017
- A Hybrid Model for Emotion Detection from TextInternational Journal of Information Retrieval Research, 2017
- Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus2017
- Emotion Extraction from Turkish Text2014
- Are They Different? Affect, Feeling, Emotion, Sentiment, and Opinion Detection in TextIEEE Transactions on Affective Computing, 2014
- Construction of a blog emotion corpus for Chinese emotional expression analysis2009
- Identifying Expressions of Emotion in Text2007
- Emotions from text2005