Towards Identifying Objectivity in Short Informal Text

Short informal texts are increasingly prevalent in modern communication, often containing fragmented grammar, personal opinions, and limited context. Traditional NLP tasks for the texts ordinarily focus on the subjective aspect learning, such as sentiment analysis and polarity classification. The st...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaowei Zhang, Cheng Zhao, Zewei Zhang, Yuchao Huang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/6/583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432689534304256
author Chaowei Zhang
Cheng Zhao
Zewei Zhang
Yuchao Huang
author_facet Chaowei Zhang
Cheng Zhao
Zewei Zhang
Yuchao Huang
author_sort Chaowei Zhang
collection DOAJ
description Short informal texts are increasingly prevalent in modern communication, often containing fragmented grammar, personal opinions, and limited context. Traditional NLP tasks for the texts ordinarily focus on the subjective aspect learning, such as sentiment analysis and polarity classification. The study of learning objectivity from the texts is similarly significant, which can benefit many real-world applications including information filtering, content verification, etc. Unfortunately, this study is not being explored. This paper proposes a novel task that aims at identifying objectivity in short informal texts. Inspired by the characteristics of objective statements that normally need complete syntax structures for knowledge expression and delivery, we try to leverage the viewpoint of subjects (U), the tense of predicates (V), and the viewpoint of objects (O) as critical factors for objectivity learning. Upon that, we further propose a two-stage objectivity identification approach: (1) a UVO quantification module is implemented via a proposed OpenIE and large language model (LLM)-based triple feature quantification procedure; (2) an objectivity identification module employs pre-trained base models like BERT or RoBERTa that are constrained with the quantified UVO. The experimental result demonstrates our approach can outperform the base models up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.91</mn><mo>%</mo></mrow></semantics></math></inline-formula> in objective-F1 and up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.97</mn><mo>%</mo></mrow></semantics></math></inline-formula> in accuracy.
format Article
id doaj-art-c432b8ba933f45d8a3a8b35159a523cd
institution Kabale University
issn 1099-4300
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-c432b8ba933f45d8a3a8b35159a523cd2025-08-20T03:27:18ZengMDPI AGEntropy1099-43002025-05-0127658310.3390/e27060583Towards Identifying Objectivity in Short Informal TextChaowei Zhang0Cheng Zhao1Zewei Zhang2Yuchao Huang3The Department of Information Engineering, Yangzhou University, Yangzhou 225012, ChinaThe Department of Information Engineering, Yangzhou University, Yangzhou 225012, ChinaThe Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36849, USAThe Future Design Laboratory of Zhejiang University, Hangzhou 310027, ChinaShort informal texts are increasingly prevalent in modern communication, often containing fragmented grammar, personal opinions, and limited context. Traditional NLP tasks for the texts ordinarily focus on the subjective aspect learning, such as sentiment analysis and polarity classification. The study of learning objectivity from the texts is similarly significant, which can benefit many real-world applications including information filtering, content verification, etc. Unfortunately, this study is not being explored. This paper proposes a novel task that aims at identifying objectivity in short informal texts. Inspired by the characteristics of objective statements that normally need complete syntax structures for knowledge expression and delivery, we try to leverage the viewpoint of subjects (U), the tense of predicates (V), and the viewpoint of objects (O) as critical factors for objectivity learning. Upon that, we further propose a two-stage objectivity identification approach: (1) a UVO quantification module is implemented via a proposed OpenIE and large language model (LLM)-based triple feature quantification procedure; (2) an objectivity identification module employs pre-trained base models like BERT or RoBERTa that are constrained with the quantified UVO. The experimental result demonstrates our approach can outperform the base models up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.91</mn><mo>%</mo></mrow></semantics></math></inline-formula> in objective-F1 and up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.97</mn><mo>%</mo></mrow></semantics></math></inline-formula> in accuracy.https://www.mdpi.com/1099-4300/27/6/583short informal textsobjectivity learningrelational tripleslarge language models
spellingShingle Chaowei Zhang
Cheng Zhao
Zewei Zhang
Yuchao Huang
Towards Identifying Objectivity in Short Informal Text
Entropy
short informal texts
objectivity learning
relational triples
large language models
title Towards Identifying Objectivity in Short Informal Text
title_full Towards Identifying Objectivity in Short Informal Text
title_fullStr Towards Identifying Objectivity in Short Informal Text
title_full_unstemmed Towards Identifying Objectivity in Short Informal Text
title_short Towards Identifying Objectivity in Short Informal Text
title_sort towards identifying objectivity in short informal text
topic short informal texts
objectivity learning
relational triples
large language models
url https://www.mdpi.com/1099-4300/27/6/583
work_keys_str_mv AT chaoweizhang towardsidentifyingobjectivityinshortinformaltext
AT chengzhao towardsidentifyingobjectivityinshortinformaltext
AT zeweizhang towardsidentifyingobjectivityinshortinformaltext
AT yuchaohuang towardsidentifyingobjectivityinshortinformaltext