A multi-label text sentiment analysis model based on sentiment correlation modeling
ObjectiveThis study proposes an emotion correlation-enhanced sentiment analysis model (ECO-SAM), a sentiment correlation modeling-based multi-label sentiment analysis model.MethodsThe ECO-SAM utilizes a pre-trained BERT encoder to obtain semantic embedding of input texts and then leverages a self-at...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-12-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2024.1490796/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846114310455033856 |
|---|---|
| author | Yingying Ni Wei Ni |
| author_facet | Yingying Ni Wei Ni |
| author_sort | Yingying Ni |
| collection | DOAJ |
| description | ObjectiveThis study proposes an emotion correlation-enhanced sentiment analysis model (ECO-SAM), a sentiment correlation modeling-based multi-label sentiment analysis model.MethodsThe ECO-SAM utilizes a pre-trained BERT encoder to obtain semantic embedding of input texts and then leverages a self-attention mechanism to model the semantic correlation between emotions. Additionally, it utilizes a text emotion matching neural network to make sentiment analysis for input texts.ResultsThe experiment results in public datasets demonstrate that compared to baseline models, the ECO-SAM obtains the precision score increasing by 13.33% at most, the recall score increasing by 3.69% at most, and the F1 score increasing by 8.44% at most. Meanwhile, the modeled sentiment semantics are interpretable.LimitationsThe data modeled by the ECO-SAM are limited to text-only modality, excluding multi-modal data that could enhance classification performance. Additionally, the training data are not large-scale, and there is a lack of high-quality large-scale training data for fine-tuning sentiment analysis models.ConclusionThe ECO-SAM is capable of effectively modeling sentiment semantics and achieving excellent classification performance in many public sentiment analysis datasets. |
| format | Article |
| id | doaj-art-c3af99c89b3e46a19f221cfa2b075730 |
| institution | Kabale University |
| issn | 1664-1078 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj-art-c3af99c89b3e46a19f221cfa2b0757302024-12-20T14:23:15ZengFrontiers Media S.A.Frontiers in Psychology1664-10782024-12-011510.3389/fpsyg.2024.14907961490796A multi-label text sentiment analysis model based on sentiment correlation modelingYingying Ni0Wei Ni1School of Media & Communication Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Critical Care Medicine, Sir Run Run Shaw Hospital, Hangzhou, Zhejiang, ChinaObjectiveThis study proposes an emotion correlation-enhanced sentiment analysis model (ECO-SAM), a sentiment correlation modeling-based multi-label sentiment analysis model.MethodsThe ECO-SAM utilizes a pre-trained BERT encoder to obtain semantic embedding of input texts and then leverages a self-attention mechanism to model the semantic correlation between emotions. Additionally, it utilizes a text emotion matching neural network to make sentiment analysis for input texts.ResultsThe experiment results in public datasets demonstrate that compared to baseline models, the ECO-SAM obtains the precision score increasing by 13.33% at most, the recall score increasing by 3.69% at most, and the F1 score increasing by 8.44% at most. Meanwhile, the modeled sentiment semantics are interpretable.LimitationsThe data modeled by the ECO-SAM are limited to text-only modality, excluding multi-modal data that could enhance classification performance. Additionally, the training data are not large-scale, and there is a lack of high-quality large-scale training data for fine-tuning sentiment analysis models.ConclusionThe ECO-SAM is capable of effectively modeling sentiment semantics and achieving excellent classification performance in many public sentiment analysis datasets.https://www.frontiersin.org/articles/10.3389/fpsyg.2024.1490796/fulltext classificationsentiment analysisnatural language processingattention mechanismemotion theory |
| spellingShingle | Yingying Ni Wei Ni A multi-label text sentiment analysis model based on sentiment correlation modeling Frontiers in Psychology text classification sentiment analysis natural language processing attention mechanism emotion theory |
| title | A multi-label text sentiment analysis model based on sentiment correlation modeling |
| title_full | A multi-label text sentiment analysis model based on sentiment correlation modeling |
| title_fullStr | A multi-label text sentiment analysis model based on sentiment correlation modeling |
| title_full_unstemmed | A multi-label text sentiment analysis model based on sentiment correlation modeling |
| title_short | A multi-label text sentiment analysis model based on sentiment correlation modeling |
| title_sort | multi label text sentiment analysis model based on sentiment correlation modeling |
| topic | text classification sentiment analysis natural language processing attention mechanism emotion theory |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2024.1490796/full |
| work_keys_str_mv | AT yingyingni amultilabeltextsentimentanalysismodelbasedonsentimentcorrelationmodeling AT weini amultilabeltextsentimentanalysismodelbasedonsentimentcorrelationmodeling AT yingyingni multilabeltextsentimentanalysismodelbasedonsentimentcorrelationmodeling AT weini multilabeltextsentimentanalysismodelbasedonsentimentcorrelationmodeling |