Towards jointly extracting aspects and aspect-specific sentiment knowledge

Xu, Xueke; Shi, Tan; Liu, Yue; Cheng, Xueqi; Lin, Zheng

doi:10.1145/2396761.2398539

Cited by 24 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it does not further identify aspect-aware sentiment polarities of opinion words, which are very important for sentiment analysis. The Joint Aspect/Sentiment model proposed in [26] detects aspect-specific opinion words and identifies the sentiment polarities of opinion words. However, it is designed for monolingual scenarios instead of multilingual ones.…”

Section: Aspect-level Sentiment Analysismentioning

confidence: 99%

“…Each sentence s in any review d is associated with an aspect variable z d,s . Similar to ASUM [11] and JAS [26], the CLJAS model also assumes that all words in a sentence are generated from the same topic. Therefore, the aspect variable, z d,s , is shared by all words in sentence s. …”

Section: The Proposed Modelmentioning

confidence: 99%

“…The value of µ was set to 0.001 for each sentiment label. Without loss of generality, Location hotel, walk, location, station, Rome, metro, walking, minutes, bus, steps, Vatican, distance, termini, Spanish, train, city, restaurants, minute, area, away, great, close, good, easy, right, quiet, attractions, nice, major, convenient the above parameters were set the same as in [26]. For the target language, the values of γ tgt src and γ tgt tgt are asymmetrical.…”

Section: Parameters Settingsmentioning

confidence: 99%

See 2 more Smart Citations

A Cross-Lingual Joint Aspect/Sentiment Model for Sentiment Analysis

Lin

Jin

et al. 2014

Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Sentiment analysis in various languages has been a research hotspot with many applications. However, sentiment resources (e.g., labeled corpora, sentiment lexicons) of different languages are unbalanced in terms of quality and quantity, which arouses interests in cross-lingual sentiment analysis aiming at using the resources in a source language to improve sentiment analysis in a target language. Nevertheless, many existing cross-lingual related works rely on a certain machine translation system to directly adapt the labeled data from the source language to the target language, which usually suffers from inaccurate results generated by the machine translation system. On the other hand, most sentiment analysis studies focus on document-level sentiment classification that cannot solve the aspect dependency problem of sentiment words. For instance, in the reviews on a cell phone, long is positive for the lifespan of its battery, but negative for the response time of its operating system. To solve these problems, this paper develops a novel Cross-Lingual Joint Aspect/Sentiment (CLJAS) model to carry out aspect-specific sentiment analysis in a target language using the knowledge learned from a source language. Specifically, the CLJAS model jointly detects aspects and sentiments of two languages simultaneously by incorporating sentiments into a cross-lingual topic model framework. Extensive experiments on different domains and different languages demonstrate that the proposed model can significantly improve the accuracy of sentiment classification in the target language.

show abstract

Section: Aspect-level Sentiment Analysismentioning

confidence: 99%

Section: The Proposed Modelmentioning

confidence: 99%

Section: Parameters Settingsmentioning

confidence: 99%

See 1 more Smart Citation

A Cross-Lingual Joint Aspect/Sentiment Model for Sentiment Analysis

Lin

Jin

et al. 2014

Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Joint Sentiment-Topic Model (JST) [10] and the Aspect and Sentiment Unification Model (ASUM) [8] model sentiments (polarities of words or sentences) and topics by introducing latent variables for polarities. The Joint Aspect/Sentiment model (JAS) [20] also has latent variables for polarities and considers reviewable aspects, such as in [8], and aspect-specific opinion words. These models do not consider domains, in contrast to our proposed model, which utilizes domain information as labels and handles domain dependence and independence.…”

Section: Related Workmentioning

confidence: 99%

“…Some reviews often have multiple domain labels, like a review of a biography of a musician, which has domain labels MUSIC and BOOK. In addition, the models in [10,8,20,21] have discrete polarities, like negative, positive, and neutral, whereas our proposed model assumes that the polarities take continuous values.…”

Section: Related Workmentioning

confidence: 99%

Domain-dependent/independent topic switching model for online reviews with numerical ratings

Ida

Nakamura

Matsumoto

2013

Proceedings of the 22nd ACM International Conference on Conference on Information &Amp; Knowledge Management - CIKM '13

View full text Add to dashboard Cite

We propose a domain-dependent/independent topic switching model based on Bayesian probabilistic modeling for modeling online product reviews that are accompanied with numerical ratings provided by users. In this model, each word is allocated to a domain-dependent topic or a domainindependent topic, and the distribution of topics in an online review is connected to an observed numerical rating via a linear regression model. Domain-dependent topics utilize domain information observed with a corpus, and domainindependent topics utilize the framework of Bayesian Nonparametrics, which can estimate the number of topics in posterior distributions. The posterior distribution is estimated via collapsed Gibbs sampling. Using real data, our proposed model had smaller mean square error and smaller average mean error with a small model size and achieved convergence in fewer iterations for a regression task involving online review ratings, outperforming a baseline model that did not consider domains. Moreover, the proposed model can also tell us whether the words are positive or negative in the form of continuous values. This feature allows us to extract domain-dependent and -independent sentiment words.

show abstract

Modeling Multi-aspect Relationship with Joint Learning for Aspect-Level Sentiment Classification

Zhou

Huang

et al. 2020

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Towards jointly extracting aspects and aspect-specific sentiment knowledge

Cited by 24 publications

References 8 publications

A Cross-Lingual Joint Aspect/Sentiment Model for Sentiment Analysis

A Cross-Lingual Joint Aspect/Sentiment Model for Sentiment Analysis

Domain-dependent/independent topic switching model for online reviews with numerical ratings

Modeling Multi-aspect Relationship with Joint Learning for Aspect-Level Sentiment Classification

Contact Info

Product

Resources

About