OPTIMIZING BERTSNN TO ENHANCE SOURCE-TARGET DOMAIN SIMILARITY SCORING FOR CROSS-DOMAIN SENTIMENT CLASSIFICATION OF PRODUCT REVIEWS.

Saved in:

Bibliographic Details
Title:	OPTIMIZING BERTSNN TO ENHANCE SOURCE-TARGET DOMAIN SIMILARITY SCORING FOR CROSS-DOMAIN SENTIMENT CLASSIFICATION OF PRODUCT REVIEWS.
Authors:	Haitao Zhao¹ andrewzhao@student.usm.my, Yan, Jasy Liew Suet¹ jasyliew@usm.my
Source:	Malaysian Journal of Computer Science. 2025 Special Issue, Vol. 38, p1-19. 19p.
Subjects:	Sentiment analysis, Domain specificity, Product reviews, Language models, Artificial neural networks, Machine learning
Abstract:	Cross-domain sentiment analysis (CDSA) predicts sentiment polarity in a target domain using knowledge from source domains but existing CDSA methods lack effective source domain selection strategies. This study investigates BertSNN, which combines pre-trained BERT embeddings, a Siamese neural network, and various distance metrics to measure domain similarity and optimize source domain selection for CDSA. First, we experiment with document-level (DocBERT) and sentence-level (SentenceBERT) embeddings with BiLSTM and BiLSTM + CNN neural network configurations to identify the best combination for BertSNN. Second, we explore two distance metrics--Euclidean and Manhattan--alongside shifted cosine similarity to determine the most effective choice for domain similarity scoring. Using product reviews, we test on 25 target domains, examining whether using multiple top most similar source domains improves cross-domain sentiment classification compared to a single most similar source domain. Results indicate that document-level embeddings, BiLSTM and shifted cosine similarity produce the most optimal BertSNN that can select high-quality similar source domains to train a cross-domain sentiment classifier for a target domain, beating two other traditional baseline methods (i.e., bagof-words and TF-IDF representations). Our findings also show that using top five most similar source domains (k = 5) for training generally improves cross-domain sentiment classification performance as opposed to using a single most similar source domain (k = 1). This study contributes to CDSA by advancing the understanding of embedding choices and distance metrics within a Siamese neural network for source-target domain similarity scoring and providing actionable insights on domain selection strategies to improve sentiment analysis models. [ABSTRACT FROM AUTHOR]
	Copyright of Malaysian Journal of Computer Science is the property of University of Malaysia, Faculty of Computer Science & Information Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Cross-domain sentiment analysis (CDSA) predicts sentiment polarity in a target domain using knowledge from source domains but existing CDSA methods lack effective source domain selection strategies. This study investigates BertSNN, which combines pre-trained BERT embeddings, a Siamese neural network, and various distance metrics to measure domain similarity and optimize source domain selection for CDSA. First, we experiment with document-level (DocBERT) and sentence-level (SentenceBERT) embeddings with BiLSTM and BiLSTM + CNN neural network configurations to identify the best combination for BertSNN. Second, we explore two distance metrics--Euclidean and Manhattan--alongside shifted cosine similarity to determine the most effective choice for domain similarity scoring. Using product reviews, we test on 25 target domains, examining whether using multiple top most similar source domains improves cross-domain sentiment classification compared to a single most similar source domain. Results indicate that document-level embeddings, BiLSTM and shifted cosine similarity produce the most optimal BertSNN that can select high-quality similar source domains to train a cross-domain sentiment classifier for a target domain, beating two other traditional baseline methods (i.e., bagof-words and TF-IDF representations). Our findings also show that using top five most similar source domains (k = 5) for training generally improves cross-domain sentiment classification performance as opposed to using a single most similar source domain (k = 1). This study contributes to CDSA by advancing the understanding of embedding choices and distance metrics within a Siamese neural network for source-target domain similarity scoring and providing actionable insights on domain selection strategies to improve sentiment analysis models. [ABSTRACT FROM AUTHOR]
ISSN:	01279084