Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review

Al-Moslmi, Tareq; Omar, Nazlia; Abdullah, Salwani; Albared, Mohammed

doi:10.1109/access.2017.2690342

Cited by 105 publications

(42 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a demand for applications and systems that can automatically extract, classify, and present opinions in real time that are supportive and easy for a tourist to interpret (Gelbard, Ramon‐Gonen, Carmeli, Bittmann, & Talyansky, ). Previous techniques (Al‐Moslmi, Omar, Abdullah, & Albared, ; Ejaz, Turabee, Rahim, & Khoja, ; Moraes, Valiati, & Neto, ; Zhang & Liu, ) emphasized classifying the opinions into different polarity classes (e.g., positive or negative and one‐to‐five stars) to fulfil this demand. However, focussing only on the polarity classes fails to adequately represent the multiple aspects around which an entity can be analysed.…”

Section: Introductionmentioning

confidence: 99%

Multiaspect‐based opinion classification model for tourist reviews

et al. 2019

View full text Add to dashboard Cite

Tourist reviews on social media websites reflect the tourist's opinions concerning various aspects of a tourist place or service (e.g., “comfortable room” and “terrible service” in hotel reviews). Extracting these aspects from reviews is a challenging task in opinion mining. Therefore, aspect‐based opinion mining has emerged as a new area of social review mining. Existing approaches in this area focus on extracting explicit aspects and classification of opinions around these aspects. However, the implicit and coreferential aspects during aspect extraction are often neglected, and the classification of multiaspect opinions is relatively less emphasized in prior art. In this paper, we propose a model, namely, “enhanced multiaspect‐based opinion classification” that addresses existing challenges by automatically extracting both explicit and implicit aspects and classifying the multiaspect opinions. In this model, first, a probabilistic co‐occurrence‐based method is proposed that utilizes the co‐occurrence between aspects and sentiment words to identify the coreferential aspects and merge them into groups. Second, an implicit aspect extraction method is proposed that associates the sentiment words with suitable aspects to build an aspect‐sentiment hierarchy. Third, a multiaspect opinion classification approach is proposed that employs multilabel classification algorithms to classify opinions into different polarity classes. The effectiveness of the proposed model is evaluated by conducting experiments on benchmark and real‐world datasets. The experimental results revealed the supremacy of multilabel classifiers by achieving 90% accuracy per label on classification when extracting 87% domain‐relevant aspects. A state‐of‐the‐art performance comparison is conducted that also verifies the advantages of the proposed model.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiaspect‐based opinion classification model for tourist reviews

et al. 2019

View full text Add to dashboard Cite

show abstract

“…We briefly review the cross-domain sentiment classification techniques relevant to our work, and some recent deep learning approaches achieving state-of-the-art performance. A recent survey on this topic can be found in [28] and a task summary in [1]. One of the most classical works in crossdomain sentiment classification is structural correspondence learning (SCL) [10].…”

Section: Related Workmentioning

confidence: 99%

Cross-Domain Sentiment Encoding through Stochastic Word Embedding

Hao

Hong

et al. 2020

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Sentiment analysis is an important topic concerning identification of feelings, attitudes, emotions and opinions from text. To automate such analysis, a large amount of example text needs to be manually annotated for model training. This is laborious and expensive, but the cross-domain technique is a key solution to reducing the cost by reusing annotated reviews across domains. However, its success largely relies on the learning of a robust common representation space across domains. In the recent years, significant effort has been invested to improve the cross-domain representation learning by designing increasingly more complex and elaborate model inputs and architectures. We support that it is not necessary to increase design complexity as this inevitably consumes more time in model training. Instead, we propose to explore the word polarity and occurrence information through a simple mapping and encode such information more accurately whilst managing lower computational costs. The proposed approach is unique and takes advantage of the stochastic embedding technique to tackle cross-domain sentiment alignment. Its effectiveness is benchmarked with over ten data tasks constructed from two review corpora and it is compared against ten classical and state-of-the-art methods.

show abstract

“…SA also been used to deal with crossdomain problem. Al-Molsmi et al [27] has tackled this issue to improve cross-domain sentiment classification by creating a resource in the form of an overview of the techniques, methods, and approaches that have been used in order to assist researchers in developing new and more accurate techniques in the future. There are few research works that are related to sentiment analysis on product reviews that were studied in this paper.…”

Section: B Sentiment Analysismentioning

confidence: 99%

Contextual Sentiment Based Recommender System to Provide Recommendation in the Electronic Products Domain

Osman

Noah

Darwich

2019

IJMLC

View full text Add to dashboard Cite

The rush to purchase the latest products sometimes prevents people from thinking things through completely. Consequently, recommender services are increasingly emerging. By looking at industry trends, interviewing dozens of leading industry stakeholders, and using publicly available information, it is important to filter out the most relevant information for consumer electronics before purchasing their items. This paper presents an electronic product recommender system based on contextual information from sentiment analysis. The recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. We present a contextual information sentiment based model for recommender system by making use of user comments and preferences to provide a recommendation. The purpose of this approach is to avoid term ambiguity which is so called domain sensitivity problem in recommendation. The proposed contextual information sentiment-based model illustrates better performance by using results of RMSE and MAE measurements as compared to the conventional collaborative filtering approach in electronic product recommendation.

show abstract

Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review

Cited by 105 publications

References 63 publications

Multiaspect‐based opinion classification model for tourist reviews

Multiaspect‐based opinion classification model for tourist reviews

Cross-Domain Sentiment Encoding through Stochastic Word Embedding

Contextual Sentiment Based Recommender System to Provide Recommendation in the Electronic Products Domain

Contact Info

Product

Resources

About