@inproceedings{islam-etal-2022-emonoba,
title = "{E}mo{N}o{B}a: A Dataset for Analyzing Fine-Grained Emotions on Noisy {B}angla Texts",
author = "Islam, Khondoker Ittehadul and
Yuvraz, Tanvir and
Islam, Md Saiful and
Hassan, Enamul",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.17",
pages = "128--134",
abstract = "For low-resourced Bangla language, works on detecting emotions on textual data suffer from size and cross-domain adaptability. In our paper, we propose a manually annotated dataset of 22,698 Bangla public comments from social media sites covering 12 different domains such as Personal, Politics, and Health, labeled for 6 fine-grained emotion categories of the Junto Emotion Wheel. We invest efforts in the data preparation to 1) preserve the linguistic richness and 2) challenge any classification model. Our experiments to develop a benchmark classification system show that random baselines perform better than neural networks and pre-trained language models as hand-crafted features provide superior performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="islam-etal-2022-emonoba">
<titleInfo>
<title>EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khondoker</namePart>
<namePart type="given">Ittehadul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanvir</namePart>
<namePart type="family">Yuvraz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Saiful</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For low-resourced Bangla language, works on detecting emotions on textual data suffer from size and cross-domain adaptability. In our paper, we propose a manually annotated dataset of 22,698 Bangla public comments from social media sites covering 12 different domains such as Personal, Politics, and Health, labeled for 6 fine-grained emotion categories of the Junto Emotion Wheel. We invest efforts in the data preparation to 1) preserve the linguistic richness and 2) challenge any classification model. Our experiments to develop a benchmark classification system show that random baselines perform better than neural networks and pre-trained language models as hand-crafted features provide superior performance.</abstract>
<identifier type="citekey">islam-etal-2022-emonoba</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.17</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>128</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts
%A Islam, Khondoker Ittehadul
%A Yuvraz, Tanvir
%A Islam, Md Saiful
%A Hassan, Enamul
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F islam-etal-2022-emonoba
%X For low-resourced Bangla language, works on detecting emotions on textual data suffer from size and cross-domain adaptability. In our paper, we propose a manually annotated dataset of 22,698 Bangla public comments from social media sites covering 12 different domains such as Personal, Politics, and Health, labeled for 6 fine-grained emotion categories of the Junto Emotion Wheel. We invest efforts in the data preparation to 1) preserve the linguistic richness and 2) challenge any classification model. Our experiments to develop a benchmark classification system show that random baselines perform better than neural networks and pre-trained language models as hand-crafted features provide superior performance.
%U https://aclanthology.org/2022.aacl-short.17
%P 128-134
Markdown (Informal)
[EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts](https://aclanthology.org/2022.aacl-short.17) (Islam et al., AACL-IJCNLP 2022)
ACL
- Khondoker Ittehadul Islam, Tanvir Yuvraz, Md Saiful Islam, and Enamul Hassan. 2022. EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 128–134, Online only. Association for Computational Linguistics.