@inproceedings{ahmadnia-etal-2024-opinion,
title = "Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States",
author = "Ahmadnia, Saeed and
Yousefi Jordehi, Arash and
Hosseini Khasheh Heyran, Mahsa and
Mirroshandel, SeyedAbolghasem and
Rambow, Owen",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1093",
pages = "12481--12495",
abstract = "Opinion mining is an important task in natural language processing. The MPQA Opinion Corpus is a fine-grained and comprehensive dataset of private states (i.e., the condition of a source who has an attitude which may be directed toward a target) based on context. Although this dataset was released years ago, because of its complex definition of annotations and hard-to-read data format, almost all existing research works have only focused on a small subset of the dataset. In this paper, we present a comprehensive study of the entire MPQA 2.0 dataset. In order to achieve this goal, we first provide a clean version of MPQA 2.0 in a more interpretable format. Then, we propose two novel approaches for opinion mining, establishing new high baselines for future work. We use two pre-trained large language models, BERT and T5, to automatically identify the type, polarity, and intensity of private states expressed in phrases, and we use T5 to detect opinion expressions and their agents (i.e., sources).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadnia-etal-2024-opinion">
<titleInfo>
<title>Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Ahmadnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Yousefi Jordehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahsa</namePart>
<namePart type="family">Hosseini Khasheh Heyran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SeyedAbolghasem</namePart>
<namePart type="family">Mirroshandel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Opinion mining is an important task in natural language processing. The MPQA Opinion Corpus is a fine-grained and comprehensive dataset of private states (i.e., the condition of a source who has an attitude which may be directed toward a target) based on context. Although this dataset was released years ago, because of its complex definition of annotations and hard-to-read data format, almost all existing research works have only focused on a small subset of the dataset. In this paper, we present a comprehensive study of the entire MPQA 2.0 dataset. In order to achieve this goal, we first provide a clean version of MPQA 2.0 in a more interpretable format. Then, we propose two novel approaches for opinion mining, establishing new high baselines for future work. We use two pre-trained large language models, BERT and T5, to automatically identify the type, polarity, and intensity of private states expressed in phrases, and we use T5 to detect opinion expressions and their agents (i.e., sources).</abstract>
<identifier type="citekey">ahmadnia-etal-2024-opinion</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1093</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12481</start>
<end>12495</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States
%A Ahmadnia, Saeed
%A Yousefi Jordehi, Arash
%A Hosseini Khasheh Heyran, Mahsa
%A Mirroshandel, SeyedAbolghasem
%A Rambow, Owen
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ahmadnia-etal-2024-opinion
%X Opinion mining is an important task in natural language processing. The MPQA Opinion Corpus is a fine-grained and comprehensive dataset of private states (i.e., the condition of a source who has an attitude which may be directed toward a target) based on context. Although this dataset was released years ago, because of its complex definition of annotations and hard-to-read data format, almost all existing research works have only focused on a small subset of the dataset. In this paper, we present a comprehensive study of the entire MPQA 2.0 dataset. In order to achieve this goal, we first provide a clean version of MPQA 2.0 in a more interpretable format. Then, we propose two novel approaches for opinion mining, establishing new high baselines for future work. We use two pre-trained large language models, BERT and T5, to automatically identify the type, polarity, and intensity of private states expressed in phrases, and we use T5 to detect opinion expressions and their agents (i.e., sources).
%U https://aclanthology.org/2024.lrec-main.1093
%P 12481-12495
Markdown (Informal)
[Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States](https://aclanthology.org/2024.lrec-main.1093) (Ahmadnia et al., LREC-COLING 2024)
ACL
- Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, SeyedAbolghasem Mirroshandel, and Owen Rambow. 2024. Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12481–12495, Torino, Italia. ELRA and ICCL.