The Biases of Pre-Trained Language Models: An Empirical Study on Prompt-Based Sentiment Analysis and Emotion Detection

Mao, Rui; Liu, Qian; He, Kai; Li, Wei; Wang, Zhaoxia

doi:10.1109/taffc.2022.3204972

Cited by 92 publications

(34 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MSM model is based on neurosymbolic learning systems. An analysis was also performed to check the bias of the pre-trained learning model for sentimental analysis and emotion detection 24 .…”

Section: Related Workmentioning

confidence: 99%

Towards improving e-commerce customer review analysis for sentiment detection

Singh

Saraswat

Azad

et al. 2022

Sci Rep

View full text Add to dashboard Cite

According to a report published by Business Wire, the market value of e-commerce reached US$ 13 trillion and is expected to reach US$ 55.6 trillion by 2027. In this rapidly growing market, product and service reviews can influence our purchasing decisions. It is challenging to manually evaluate reviews to make decisions and examine business models. However, users can examine and automate this process with Natural Language Processing (NLP). NLP is a well-known technique for evaluating and extracting information from written or audible texts. NLP research investigates the social architecture of societies. This article analyses the Amazon dataset using various combinations of voice components and deep learning. The suggested module focuses on identifying sentences as ‘Positive‘, ‘Neutral‘, ‘Negative‘, or ‘Indifferent‘. It analyses the data and labels the ‘better’ and ‘worse’ assumptions as positive and negative, respectively. With the expansion of the internet and e-commerce websites over the past decade, consumers now have a vast selection of products within the same domain, and NLP plays a vital part in classifying products based on evaluations. It is possible to predict sponsored and unpaid reviews using NLP with Machine Learning. This article examined various Machine Learning algorithms for predicting the sentiment of e-commerce website reviews. The automation achieves a maximum validation accuracy of 79.83% when using Fast Text as word embedding and the Multi-channel Convolution Neural Network.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards improving e-commerce customer review analysis for sentiment detection

Singh

Saraswat

Azad

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Linguistic metaphor identification has been widely studied with the help of two shared tasks (Leong et al, 2018(Leong et al, , 2020 and the large-scale annotated VUA dataset (Steen et al, 2010b). Scholars have also noticed the connection between linguistic metaphor processing and other tasks, such as affective computing (Xing et al, 2020;Duong et al, 2022;Mao et al, 2022b;Cambria et al, 2022a;Ma et al, 2023). However, there are sub-types of linguistic metaphors that have not been well studied yet, such as extended metaphors and metaphoric MWEs.…”

Section: Discussionmentioning

confidence: 99%

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Mao

Cambria

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Metaphor is a figurative language that has been frequently used in our daily lives. Due to its significance for downstream natural language processing tasks, such as machine translation and sentiment analysis, computational metaphor processing has set off an upsurge in the community. With the development of Artificial Intelligence, an increasing number of technological tools and frameworks have been proposed in this domain. In this article, we aim to comprehensively summarize and categorize previous computational metaphor processing approaches regarding metaphor identification, interpretation, generation, and application. Meanwhile, we compare the strengths and weaknesses of current works and conceive future directions in this field.

show abstract

“…Empirical study was performed on prompt-based sentiment analysis and emotion detection 19 in order to understand the bias towards pre-trained models applied for affective computing. The findings suggest that the number of label classes, emotional label-word selections, prompt templates and positions, and the word forms of emotion lexicons are factors that biased the pre-trained models 20 .…”

Section: Related Workmentioning

confidence: 98%

“…This work discusses about the way for the development of more bioinspired approaches to the design of intelligent sentiment-mining systems that can handle semantic knowledge, make analogies, learn new affective knowledge, and detect, perceive, and “feel” emotions. In 20 , the authors proposed commonsense-based neurosymbolic framework that employed unsupervised and reproducible subsymbolic techniques such as auto-regressive language models and kernel methods to build trustworthy symbolic representations that convert natural language to a sort of protolanguage and, hence, extract polarity from text in a completely interpretable and explainable manner 22 , 23 .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning based sentiment analysis and offensive language identification on multilingual code-mixed data

Shanmugavadivel¹,

Sathishkumar

Raja³

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Sentiment analysis is a process in Natural Language Processing that involves detecting and classifying emotions in texts. The emotion is focused on a specific thing, an object, an incident, or an individual. Although some tasks are concerned with detecting the existence of emotion in text, others are concerned with finding the polarities of the text, which is classified as positive, negative, or neutral. The task of determining whether a comment contains inappropriate text that affects either individual or group is called offensive language identification. The existing research has concentrated more on sentiment analysis and offensive language identification in a monolingual data set than code-mixed data. Code-mixed data is framed by combining words and phrases from two or more distinct languages in a single text. It is quite challenging to identify emotion or offensive terms in the comments since noise exists in code-mixed data. The majority of advancements in hostile language detection and sentiment analysis are made on monolingual data for languages with high resource requirements. The proposed system attempts to perform both sentiment analysis and offensive language identification for low resource code-mixed data in Tamil and English using machine learning, deep learning and pre-trained models like BERT, RoBERTa and adapter-BERT. The dataset utilized for this research work is taken from a shared task on Multi task learning DravidianLangTech@ACL2022. Another challenge addressed by this work is the extraction of semantically meaningful information from code-mixed data using word embedding. The result represents an adapter-BERT model gives a better accuracy of 65% for sentiment analysis and 79% for offensive language identification when compared with other trained models.

show abstract

The Biases of Pre-Trained Language Models: An Empirical Study on Prompt-Based Sentiment Analysis and Emotion Detection

Cited by 92 publications

References 38 publications

Towards improving e-commerce customer review analysis for sentiment detection

Towards improving e-commerce customer review analysis for sentiment detection

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Deep learning based sentiment analysis and offensive language identification on multilingual code-mixed data

Contact Info

Product

Resources

About