Research on semantic orientation classification of chinese online product reviews based on multi-aspect sentiment analysis

Sun, Qing; Niu, Jianwei; Yao, Zhong; Qiu, Dongmin

doi:10.1145/3006299.3006325

Cited by 12 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, predominant multilabel classification algorithms such as binary relevance (BR; Luaces, Díez, Barranquero, del Coz, & Bahamonde, 2012), classifier chains (CCs; Read, Pfahringer, Holmes, & Frank, 2009), multilabel k-nearest neighbour (ML-kNN; Zhang & Zhou, 2007), RAkEL d (Tsoumakas, Katakis, & Vlahavas, 2011), and ensemble CCs (ECCs; Read, Pfahringer, Holmes, & Frank, 2011) were selected and applied on each dataset individually to perform experiments. The experiment results express that the proposed model with multilabel classification algorithms is more effective and accurate compared with the existing models (Ahiladas et al, 2015;Sun et al, 2016;Wang, Wang, & Song, 2017) in the tourism domain. The proposed model provided considerably improved performance, with 90% accuracy per label on ECC and 86% average precision on BR.…”

mentioning

confidence: 64%

“…The topic with maximum probability is labelled an implicit aspect to the review. Similarly, Sun et al () proposed an LDA‐based method that randomly chose a topic from the topic distribution in review and then generated a word from the chosen topic according to the corresponding topic‐word distribution. Topic model‐based methods are governed by “higher‐order co‐occurrence.” The limitations are frequent, but irrelevant aspects are extracted incorrectly; infrequent but valid aspects can be overlooked.…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, a number of aspect‐based opinion mining approaches (Afzaal, Usman, Fong, Fong, & Zhuang, ; Kayaalp, Weckman, Ii, Millie, & Celikbilek, ; Panchendrarajan et al, ; Sun, Niu, Yao, & Qiu, ; Tsai, Wang, Chung, Su, & Tsai, ) have been proposed. However, there remain several challenges that place barriers to the effectiveness of existing approaches.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, a number of aspect-based opinion mining approaches (Afzaal, Usman, Fong, Fong, & Zhuang, 2016;Kayaalp, Weckman, Ii, Millie, & Celikbilek, 2017;Panchendrarajan et al, 2017;Sun, Niu, Yao, & Qiu, 2016;Tsai, Wang, Chung, Su, & Tsai, 2016) have been proposed.…”

mentioning

confidence: 99%

See 3 more Smart Citations

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

mentioning

confidence: 64%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Multiaspect‐based opinion classification model for tourist reviews

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Their trial demonstrates that the proposed system is exceptionally encouraging in playing out its undertakings. This paper [20] addresses the issue of multi-perspective assumption investigation of product review. Proposed semantic features mining and lexicon-based techniques to investigate the aspect-level sentiment analysis.…”

Section: Related Workmentioning

confidence: 99%

Emotions Identification by Using Unsupervised Aspect Category Based Sentiment Classification

Shinde*¹,

Pawar²,

Ahirrao³

et al. 2019

IJEAT

View full text Add to dashboard Cite

The social media is growing at an astonishing rate; this has resulted in increased online communications. The online communication contains feedbacks, comments, and reviews that are posted on the internet by users. To analyze such data, the paper represents the Aspect-based unsupervised method that applies association rule mining on customer reviews aims to algorithmically identify product aspects, their corresponding opinions from a collection of opinionated reviews. This framework involves four main subtasks: Product aspect identification, Sentiment expression identification, Emotion Detection, Comparison of Products. This paper also represents a Comparative study of sentiment analysis techniques including machine learning technique and lexicon based technique. The comparisons are majorly drawn based on features such as techniques, data source, data scope, and limitations. The proposed framework performs well with F1-Score 76.426%.

show abstract

Aspect Level Sentiment Analysis with Aspect Attention

Wang

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Research on semantic orientation classification of chinese online product reviews based on multi-aspect sentiment analysis

Cited by 12 publications

References 17 publications

Multiaspect‐based opinion classification model for tourist reviews

Multiaspect‐based opinion classification model for tourist reviews

Emotions Identification by Using Unsupervised Aspect Category Based Sentiment Classification

Aspect Level Sentiment Analysis with Aspect Attention

Contact Info

Product

Resources

About