TY - JOUR
T1 - Multi-Label Emotion Classification on Code-Mixed Text
T2 - Data and Methods
AU - Ameer, Iqra
AU - Sidorov, Grigori
AU - Gomez-Adorno, Helena
AU - Nawab, Rao Muhammad Adeel
N1 - Publisher Copyright:
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
PY - 2022
Y1 - 2022
N2 - The multi-label emotion classification task aims to identify all possible emotions in a written text that best represent the author's mental state. In recent years, multi-label emotion classification attracted the attention of researchers due to its potential applications in e-learning, health care, marketing, etc. There is a need for standard benchmark corpora to develop and evaluate multi-label emotion classification methods. The majority of benchmark corpora were developed for the English language (monolingual corpora) using tweets. However, the multi-label emotion classification problem is not explored for code-mixed text, for example, English and Roman Urdu, although the code-mixed text is widely used in Facebook posts/comments, tweets, SMS messages, particularly by the South Asian community. For filling this gap, this study presents a large benchmark corpus for the multi-label emotion classification task, which comprises 11,914 code-mixed (English and Roman Urdu) SMS messages. Each code-mixed (English and Roman Urdu) SMS message manually annotated using a set of 12 emotions, including anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise, trust, and neutral (no emotion). As a secondary contribution, we applied and compared state-of-the-art classical machine learning (content-based methods – three word n-gram features and eight character n-gram features), deep learning (CNN, RNN, Bi-RNN, GRU, Bi-GRU, LSTM, and Bi-LSTM), and transfer learning-based methods (BERT and XLNet) on our proposed corpus. After our extensive experimentation, the best results were obtained using state-of-the-art classical machine learning methods on word uni-gram (Micro Precision = 0.67, Micro Recall = 0.54, Micro F1 = 0.67) with a combination of OVR multi-label and SVC single-label machine learning algorithms. Our proposed corpus is free and publicly available for research purposes to foster research in an under-resourced language (Roman Urdu).
AB - The multi-label emotion classification task aims to identify all possible emotions in a written text that best represent the author's mental state. In recent years, multi-label emotion classification attracted the attention of researchers due to its potential applications in e-learning, health care, marketing, etc. There is a need for standard benchmark corpora to develop and evaluate multi-label emotion classification methods. The majority of benchmark corpora were developed for the English language (monolingual corpora) using tweets. However, the multi-label emotion classification problem is not explored for code-mixed text, for example, English and Roman Urdu, although the code-mixed text is widely used in Facebook posts/comments, tweets, SMS messages, particularly by the South Asian community. For filling this gap, this study presents a large benchmark corpus for the multi-label emotion classification task, which comprises 11,914 code-mixed (English and Roman Urdu) SMS messages. Each code-mixed (English and Roman Urdu) SMS message manually annotated using a set of 12 emotions, including anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise, trust, and neutral (no emotion). As a secondary contribution, we applied and compared state-of-the-art classical machine learning (content-based methods – three word n-gram features and eight character n-gram features), deep learning (CNN, RNN, Bi-RNN, GRU, Bi-GRU, LSTM, and Bi-LSTM), and transfer learning-based methods (BERT and XLNet) on our proposed corpus. After our extensive experimentation, the best results were obtained using state-of-the-art classical machine learning methods on word uni-gram (Micro Precision = 0.67, Micro Recall = 0.54, Micro F1 = 0.67) with a combination of OVR multi-label and SVC single-label machine learning algorithms. Our proposed corpus is free and publicly available for research purposes to foster research in an under-resourced language (Roman Urdu).
KW - Annotations
KW - Benchmark testing
KW - Electronic mail
KW - Guidelines
KW - Social networking (online)
KW - Standards
KW - Task analysis
UR - http://www.scopus.com/inward/record.url?scp=85123291375&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2022.3143819
DO - 10.1109/ACCESS.2022.3143819
M3 - Artículo
AN - SCOPUS:85123291375
SN - 2169-3536
VL - 10
SP - 8779
EP - 8789
JO - IEEE Access
JF - IEEE Access
ER -