IIM: an information interaction mechanism for aspect-based sentiment analysis
ABSTRACTTerm polarity co-extraction is an aspect-based sentiment analysis task, which has been widely used in the fields of user opinions extraction. It consists of two subtasks: aspect term extraction and aspect sentiment classification. Most existing studies solve aforesaid subtasks as independent...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/09540091.2023.2283390 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850227701914271744 |
|---|---|
| author | Le Chen Lina Ge Wei Zhou |
| author_facet | Le Chen Lina Ge Wei Zhou |
| author_sort | Le Chen |
| collection | DOAJ |
| description | ABSTRACTTerm polarity co-extraction is an aspect-based sentiment analysis task, which has been widely used in the fields of user opinions extraction. It consists of two subtasks: aspect term extraction and aspect sentiment classification. Most existing studies solve aforesaid subtasks as independent tasks or simply unify the two subtasks without making full use of the relationship between tasks to mine the interaction of text information, which leads to low performance for practical applications. Meanwhile, the learning framework for these studies has a label drift phenomenon (LDP) in the process of predictive learning, increasing the learning error rate. To address the above problems, this study unifies subtasks and proposes a Unified framework based on the information interaction mechanism framework, called IIM. Specifically, we design an Information Interaction Channel (IIC) to construct closer semantic features to extract preliminary term-polarity unified labels from the perspective of basic semantics. For label inconsistency between aspect terms, a Position-aware Module (SAM) is proposed to alleviate the Label Drift Phenomenon (LDP). Moreover, we introduce a syntax-attention graph neural network (Syn-AttGCN) to model the syntactic structure of text and strengthen the emotional connection between aspect terms. The experimental results show that IIM outperforms most baselines. Meanwhile, the SAM module has a certain slowing effect on LDP. |
| format | Article |
| id | doaj-art-ec72702840ab4fb1bf8da98786fa8c71 |
| institution | OA Journals |
| issn | 0954-0091 1360-0494 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj-art-ec72702840ab4fb1bf8da98786fa8c712025-08-20T02:04:44ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.2283390IIM: an information interaction mechanism for aspect-based sentiment analysisLe Chen0Lina Ge1Wei Zhou2Institute for Artificial Intelligence, Guangxi Minzu University, Nan Ning, ChinaInstitute for Artificial Intelligence, Guangxi Minzu University, Nan Ning, ChinaInstitute for Artificial Intelligence, Guangxi Minzu University, Nan Ning, ChinaABSTRACTTerm polarity co-extraction is an aspect-based sentiment analysis task, which has been widely used in the fields of user opinions extraction. It consists of two subtasks: aspect term extraction and aspect sentiment classification. Most existing studies solve aforesaid subtasks as independent tasks or simply unify the two subtasks without making full use of the relationship between tasks to mine the interaction of text information, which leads to low performance for practical applications. Meanwhile, the learning framework for these studies has a label drift phenomenon (LDP) in the process of predictive learning, increasing the learning error rate. To address the above problems, this study unifies subtasks and proposes a Unified framework based on the information interaction mechanism framework, called IIM. Specifically, we design an Information Interaction Channel (IIC) to construct closer semantic features to extract preliminary term-polarity unified labels from the perspective of basic semantics. For label inconsistency between aspect terms, a Position-aware Module (SAM) is proposed to alleviate the Label Drift Phenomenon (LDP). Moreover, we introduce a syntax-attention graph neural network (Syn-AttGCN) to model the syntactic structure of text and strengthen the emotional connection between aspect terms. The experimental results show that IIM outperforms most baselines. Meanwhile, the SAM module has a certain slowing effect on LDP.https://www.tandfonline.com/doi/10.1080/09540091.2023.2283390Aspect-based sentiment analysisterm polarity co-extractionaspect term extractionaspect sentiment classificationlabel drift phenomenon (LDP)information interaction mechanism (IIM) |
| spellingShingle | Le Chen Lina Ge Wei Zhou IIM: an information interaction mechanism for aspect-based sentiment analysis Connection Science Aspect-based sentiment analysis term polarity co-extraction aspect term extraction aspect sentiment classification label drift phenomenon (LDP) information interaction mechanism (IIM) |
| title | IIM: an information interaction mechanism for aspect-based sentiment analysis |
| title_full | IIM: an information interaction mechanism for aspect-based sentiment analysis |
| title_fullStr | IIM: an information interaction mechanism for aspect-based sentiment analysis |
| title_full_unstemmed | IIM: an information interaction mechanism for aspect-based sentiment analysis |
| title_short | IIM: an information interaction mechanism for aspect-based sentiment analysis |
| title_sort | iim an information interaction mechanism for aspect based sentiment analysis |
| topic | Aspect-based sentiment analysis term polarity co-extraction aspect term extraction aspect sentiment classification label drift phenomenon (LDP) information interaction mechanism (IIM) |
| url | https://www.tandfonline.com/doi/10.1080/09540091.2023.2283390 |
| work_keys_str_mv | AT lechen iimaninformationinteractionmechanismforaspectbasedsentimentanalysis AT linage iimaninformationinteractionmechanismforaspectbasedsentimentanalysis AT weizhou iimaninformationinteractionmechanismforaspectbasedsentimentanalysis |