Attention Based Shared Representation for Multi-task Stance Detection and Sentiment Analysis

Chauhan, Dushyant Singh; Kumar, Rohan; Ekbal, Asif

doi:10.1007/978-3-030-36802-9_70

Cited by 12 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their study, the researchers used a sentiment lexicon along with to build a stance lexicon and incorporated it for the attention layer in the model. Another work by [47] used sentiment as an auxiliary task to predict the stance using a SemEval stance dataset.…”

Section: Stance Vs Sentiment Quantitativelymentioning

confidence: 99%

Stance detection on social media: State of the art and trends

Aldayel

Magdy

2021

Information Processing & Management

153

View full text Add to dashboard Cite

Section: Stance Vs Sentiment Quantitativelymentioning

confidence: 99%

Stance detection on social media: State of the art and trends

Aldayel

Magdy

2021

Information Processing & Management

153

View full text Add to dashboard Cite

“…Their MTL model achieved a 14.4% higher macro-F1 score than state-of-the-art (SOTA) models on the FNC-1 dataset [49]. Only a few studies have investigated the joint learning of stance and sentiment detection through MTL [10,11,50,51]. Sun et al [10] proposed an LSTM-based model to simultaneously capture the stance and sentiment information of a post; however, their model does not incorporate an attention mechanism.…”

Section: Related Workmentioning

confidence: 99%

“…Equal weighting assigns the same weight to each task loss. In the domain of stance detection, all existing studies that have proposed MTL models have uniformly adopted equal weighting for the associated tasks [10,11,48,50,51,59,60]. While this approach is straightforward, it operates under the assumption that all tasks bear equal importance, an assumption that does not hold true for various NLP tasks.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Stance Detection through Sequential Weighted Multi-task Learning

Alturayeif

Luqman

Ahmed

2023

Preprint

View full text Add to dashboard Cite

The exponential growth of user-generated content on social media platforms, online news outlets, and digital communication has necessitated the development of automated tools for analyzing opinions and attitudes expressed in text. Stance detection, a critical task in Natural Language Processing (NLP), aims to identify the underlying perspective or viewpoint of an individual or group towards a specific topic or target. This paper explores the challenges of stance detection, particularly in the context of social media, where brevity, informality, and limited contextual information prevail. While sentiment analysis focuses on explicit sentiment polarity, stance detection classifies the stance or viewpoint of a text towards a target, often of an abstract nature. This study introduces two multi-task learning (MTL) models that integrate sentiment analysis and sarcasm detection tasks to enhance stance detection performance. Four task weighting techniques are proposed and evaluated, and their effectiveness in the MTL models is demonstrated. Extensive evaluations on English and Arabic benchmark datasets highlight the advantages of the proposed models. Among them, the multi-target sequential MTL model stands out with its hierarchical weighting approach, as it achieves state-of-the-art performance. The study underscores the potential of MTL in improving stance detection and provides insights into the interaction between sentiment and stance, while considering the impact of sarcasm.

show abstract

“…The study by (Li and Caragea 2019) uses sentiment to predict the stance through a multi-task learning model. Another work by (Chauhan, Kumar, and Ekbal 2019) uses sentiment as an auxiliary task to predict attitude. However, in our work, multiple features in the form of text and topic words are used to separate the task-dependent and independent feature spaces and perform both tasks simultaneously by using attention frameworks to focus on the most important feature representations and discarding the useless shared features that may affect the performance of both tasks.…”

Section: Related Workmentioning

confidence: 99%

A Multi-Task Model for Sentiment Aided Stance Detection of Climate Change Tweets

Upadhyaya

Fisichella

Nejdl

2023

ICWSM

View full text Add to dashboard Cite

Climate change has become one of the biggest challenges of our time. Social media platforms such as Twitter play an important role in raising public awareness and spreading knowledge about the dangers of the current climate crisis. With the increasing number of campaigns and communication about climate change through social media, the information could create more awareness and reach the general public and policy makers. However, these Twitter communications lead to polarization of beliefs, opinion-dominated ideologies, and often a split into two communities of climate change deniers and believers. In this paper, we propose a framework that helps identify denier statements on Twitter and thus classifies the stance of the tweet into one of the two attitudes towards climate change (denier/believer). The sentimental aspects of Twitter data on climate change are deeply rooted in general public attitudes toward climate change. Therefore, our work focuses on learning two closely related tasks: Stance Detection and Sentiment Analysis of climate change tweets. We propose a multi-task framework that performs stance detection (primary task) and sentiment analysis (auxiliary task) simultaneously. The proposed model incorporates the feature-specific and shared-specific attention frameworks to fuse multiple features and learn the generalized features for both tasks. The experimental results show that the proposed framework increases the performance of the primary task, i.e., stance detection by benefiting from the auxiliary task, i.e., sentiment analysis compared to its uni-modal and single-task variants.

show abstract

Attention Based Shared Representation for Multi-task Stance Detection and Sentiment Analysis

Cited by 12 publications

References 11 publications

Stance detection on social media: State of the art and trends

Stance detection on social media: State of the art and trends

Enhancing Stance Detection through Sequential Weighted Multi-task Learning

A Multi-Task Model for Sentiment Aided Stance Detection of Climate Change Tweets

Contact Info

Product

Resources

About