Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis
Prompt engineering is essential for optimizing the performance of large-language models (LLMs), particularly in tasks requiring complex interpretations such as aspect-based sentiment analysis (ABSA). However, existing methodologies often struggle to detect implicit targets, especially in multi-opini...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10994766/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849328568010539008 |
|---|---|
| author | Mohammad Radi Nazlia Omar Wandeep Kaur |
| author_facet | Mohammad Radi Nazlia Omar Wandeep Kaur |
| author_sort | Mohammad Radi |
| collection | DOAJ |
| description | Prompt engineering is essential for optimizing the performance of large-language models (LLMs), particularly in tasks requiring complex interpretations such as aspect-based sentiment analysis (ABSA). However, existing methodologies often struggle to detect implicit targets, especially in multi-opinion sentences where sentiments are directed toward aspects that are not explicitly mentioned. This study addresses this gap by proposing the Iterative Syntactic-Guided Chain of Thought (IS-COT) framework, which integrates dependency parsing with modular prompt engineering to enhance LLMs’ reasoning capabilities. IS-COT leverages syntactic structures and iterative refinement to detect both explicit and implicit targets while resolving ambiguities in multi-opinion contexts. Experimental evaluations on benchmark datasets, Sem-Eval 2015 (Res15) and Sem-Eval 2016 (Res16), demonstrated the effectiveness of the framework, achieving superior performance with 80.43 F1 scores on Res15 and 84.47 F1 scores on Res16, significantly outperforming state-of-the-art models. These results highlight IS-COT’s potential of IS-COT as a comprehensive and interpretable solution for ABSA, addressing the critical limitations of existing approaches and advancing the field through innovative syntactic and semantic integration. |
| format | Article |
| id | doaj-art-16e8c53bd2e441d4ac56463f25fc1ce1 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-16e8c53bd2e441d4ac56463f25fc1ce12025-08-20T03:47:33ZengIEEEIEEE Access2169-35362025-01-0113847388475110.1109/ACCESS.2025.356869510994766Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment AnalysisMohammad Radi0https://orcid.org/0000-0001-8434-1715Nazlia Omar1https://orcid.org/0000-0002-8173-8933Wandeep Kaur2Center for Artificial Intelligence Technology (CAIT), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, MalaysiaCenter for Artificial Intelligence Technology (CAIT), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, MalaysiaCenter for Artificial Intelligence Technology (CAIT), Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, MalaysiaPrompt engineering is essential for optimizing the performance of large-language models (LLMs), particularly in tasks requiring complex interpretations such as aspect-based sentiment analysis (ABSA). However, existing methodologies often struggle to detect implicit targets, especially in multi-opinion sentences where sentiments are directed toward aspects that are not explicitly mentioned. This study addresses this gap by proposing the Iterative Syntactic-Guided Chain of Thought (IS-COT) framework, which integrates dependency parsing with modular prompt engineering to enhance LLMs’ reasoning capabilities. IS-COT leverages syntactic structures and iterative refinement to detect both explicit and implicit targets while resolving ambiguities in multi-opinion contexts. Experimental evaluations on benchmark datasets, Sem-Eval 2015 (Res15) and Sem-Eval 2016 (Res16), demonstrated the effectiveness of the framework, achieving superior performance with 80.43 F1 scores on Res15 and 84.47 F1 scores on Res16, significantly outperforming state-of-the-art models. These results highlight IS-COT’s potential of IS-COT as a comprehensive and interpretable solution for ABSA, addressing the critical limitations of existing approaches and advancing the field through innovative syntactic and semantic integration.https://ieeexplore.ieee.org/document/10994766/Aspect-based sentiment analysis (ABSA)prompt engineeringchain of thought (COT)explicit opinionimplicit opiniontarget-aspect-sentiment (TASD) |
| spellingShingle | Mohammad Radi Nazlia Omar Wandeep Kaur Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis IEEE Access Aspect-based sentiment analysis (ABSA) prompt engineering chain of thought (COT) explicit opinion implicit opinion target-aspect-sentiment (TASD) |
| title | Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis |
| title_full | Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis |
| title_fullStr | Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis |
| title_full_unstemmed | Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis |
| title_short | Syntactic-Guided Chain of Thought for Iterative Implicit and Explicit Target Detection in Aspect-Based Sentiment Analysis |
| title_sort | syntactic guided chain of thought for iterative implicit and explicit target detection in aspect based sentiment analysis |
| topic | Aspect-based sentiment analysis (ABSA) prompt engineering chain of thought (COT) explicit opinion implicit opinion target-aspect-sentiment (TASD) |
| url | https://ieeexplore.ieee.org/document/10994766/ |
| work_keys_str_mv | AT mohammadradi syntacticguidedchainofthoughtforiterativeimplicitandexplicittargetdetectioninaspectbasedsentimentanalysis AT nazliaomar syntacticguidedchainofthoughtforiterativeimplicitandexplicittargetdetectioninaspectbasedsentimentanalysis AT wandeepkaur syntacticguidedchainofthoughtforiterativeimplicitandexplicittargetdetectioninaspectbasedsentimentanalysis |