Emotion classification for short texts: an improved multi-label method
Abstract The process of computationally identifying and categorizing opinions expressed in a piece of text is of great importance to support better understanding and services to online users in the digital environment. However, accurate and fast multi-label automatic classification is still insuffic...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer Nature
2023-06-01
|
Series: | Humanities & Social Sciences Communications |
Online Access: | https://doi.org/10.1057/s41599-023-01816-6 |
_version_ | 1797806845257056256 |
---|---|
author | Xuan Liu Tianyi Shi Guohui Zhou Mingzhe Liu Zhengtong Yin Lirong Yin Wenfeng Zheng |
author_facet | Xuan Liu Tianyi Shi Guohui Zhou Mingzhe Liu Zhengtong Yin Lirong Yin Wenfeng Zheng |
author_sort | Xuan Liu |
collection | DOAJ |
description | Abstract The process of computationally identifying and categorizing opinions expressed in a piece of text is of great importance to support better understanding and services to online users in the digital environment. However, accurate and fast multi-label automatic classification is still insufficient. By considering not only individual in-sentence features but also the features in the adjacent sentences and the full text of the tweet, this study adjusted the Multi-label K-Nearest Neighbors (MLkNN) classifier to allow iterative corrections of the multi-label emotion classification. It applies the new method to improve both the accuracy and speed of emotion classification for short texts on Twitter. By carrying out three groups of experiments on the Twitter corpus, this study compares the performance of the base classifier of MLkNN, the sample-based MLkNN (S-MLkNN), and the label-based MLkNN (L-MLkNN). The results show that the improved MLkNN algorithm can effectively improve the accuracy of emotion classification of short texts, especially when the value of K in the MLkNN base classifier is 8, and the value of α is 0.7, and the improved L-MLkNN algorithm outperforms the other methods in the overall performance and the recall rate reaches 0.8019. This study attempts to obtain an efficient classifier with smaller training samples and lower training costs for sentiment analysis. It is suggested that future studies should pay more attention to balancing the efficiency of the model with smaller training sample sizes and the completeness of the model to cover various scenarios. |
first_indexed | 2024-03-13T06:13:32Z |
format | Article |
id | doaj.art-5fae662a52e94a6194b387aa00ca8034 |
institution | Directory Open Access Journal |
issn | 2662-9992 |
language | English |
last_indexed | 2024-03-13T06:13:32Z |
publishDate | 2023-06-01 |
publisher | Springer Nature |
record_format | Article |
series | Humanities & Social Sciences Communications |
spelling | doaj.art-5fae662a52e94a6194b387aa00ca80342023-06-11T11:08:38ZengSpringer NatureHumanities & Social Sciences Communications2662-99922023-06-011011910.1057/s41599-023-01816-6Emotion classification for short texts: an improved multi-label methodXuan Liu0Tianyi Shi1Guohui Zhou2Mingzhe Liu3Zhengtong Yin4Lirong Yin5Wenfeng Zheng6School of Public Affairs and Administration, University of Electronic Science and Technology of ChinaSchool of Automation, University of Electronic Science and Technology of ChinaSchool of Public Affairs and Administration, University of Electronic Science and Technology of ChinaSchool of Data Science and Artificial Intelligence, Wenzhou University of TechnologyCollege of Resource and Environment Engineering, Guizhou UniversityDepartment of Geography and Anthropology, Louisiana State UniversitySchool of Automation, University of Electronic Science and Technology of ChinaAbstract The process of computationally identifying and categorizing opinions expressed in a piece of text is of great importance to support better understanding and services to online users in the digital environment. However, accurate and fast multi-label automatic classification is still insufficient. By considering not only individual in-sentence features but also the features in the adjacent sentences and the full text of the tweet, this study adjusted the Multi-label K-Nearest Neighbors (MLkNN) classifier to allow iterative corrections of the multi-label emotion classification. It applies the new method to improve both the accuracy and speed of emotion classification for short texts on Twitter. By carrying out three groups of experiments on the Twitter corpus, this study compares the performance of the base classifier of MLkNN, the sample-based MLkNN (S-MLkNN), and the label-based MLkNN (L-MLkNN). The results show that the improved MLkNN algorithm can effectively improve the accuracy of emotion classification of short texts, especially when the value of K in the MLkNN base classifier is 8, and the value of α is 0.7, and the improved L-MLkNN algorithm outperforms the other methods in the overall performance and the recall rate reaches 0.8019. This study attempts to obtain an efficient classifier with smaller training samples and lower training costs for sentiment analysis. It is suggested that future studies should pay more attention to balancing the efficiency of the model with smaller training sample sizes and the completeness of the model to cover various scenarios.https://doi.org/10.1057/s41599-023-01816-6 |
spellingShingle | Xuan Liu Tianyi Shi Guohui Zhou Mingzhe Liu Zhengtong Yin Lirong Yin Wenfeng Zheng Emotion classification for short texts: an improved multi-label method Humanities & Social Sciences Communications |
title | Emotion classification for short texts: an improved multi-label method |
title_full | Emotion classification for short texts: an improved multi-label method |
title_fullStr | Emotion classification for short texts: an improved multi-label method |
title_full_unstemmed | Emotion classification for short texts: an improved multi-label method |
title_short | Emotion classification for short texts: an improved multi-label method |
title_sort | emotion classification for short texts an improved multi label method |
url | https://doi.org/10.1057/s41599-023-01816-6 |
work_keys_str_mv | AT xuanliu emotionclassificationforshorttextsanimprovedmultilabelmethod AT tianyishi emotionclassificationforshorttextsanimprovedmultilabelmethod AT guohuizhou emotionclassificationforshorttextsanimprovedmultilabelmethod AT mingzheliu emotionclassificationforshorttextsanimprovedmultilabelmethod AT zhengtongyin emotionclassificationforshorttextsanimprovedmultilabelmethod AT lirongyin emotionclassificationforshorttextsanimprovedmultilabelmethod AT wenfengzheng emotionclassificationforshorttextsanimprovedmultilabelmethod |