Extracting implicit features in online customer reviews for opinion mining

Zhang, Yu; Zhu, Weixiang

doi:10.1145/2487788.2487835

Cited by 49 publications

(32 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison with the method of Zhang & Zhu [10] is given in Table 1. To increase comparability, both methods are tested with all sixteen possible Partof-Speech filters (only the best one is reported).…”

Section: Discussionmentioning

confidence: 99%

“…Instead of using annotated explicit features, [10] uses the idea of double propagation [7] to find a set of explicit words and a set of opinion words. An advantage is that the found explicit features are already linked to appropriate opinion words.…”

Section: Related Workmentioning

confidence: 99%

“…However, there are several drawbacks that are apparent, both in [5], [9], and in [10]. The first problem is that only features that have been found as explicit features somewhere in the corpus can be chosen as implicit features.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Finding Implicit Features in Consumer Reviews for Sentiment Analysis

Schouten

Frăsincar

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. With the explosion of e-commerce shopping, customer reviews on the Web have become essential in the decision making process for consumers. Much of the research in this field focuses on explicit feature extraction and sentiment extraction. However, implicit feature extraction is a relatively new research field. Whereas previous works focused on finding the correct implicit feature in a sentence, given the fact that one is known to be present, this research aims at finding the right implicit feature without this pre-knowledge. Potential implicit features are assigned a score based on their co-occurrence frequencies with the words of a sentence, with the highest-scoring one being assigned to that sentence. To distinguish between sentences that have an implicit feature and the ones that do not, a threshold parameter is introduced, filtering out potential features whose score is too low. Using restaurant reviews and product reviews, the threshold-based approach improves the F1-measure by 3.6 and 8.7 percentage points, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Finding Implicit Features in Consumer Reviews for Sentiment Analysis

Schouten

Frăsincar

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Even though the paper attempts to give a more aspect level detailed approach, it lacks in dealing with multi words like "hard disk", "battery life" which introduces a significant amount of error in their results. To overcome the significant challenge faced in [1] with respect to category detection, the authors of [3] have taken an algorithm, being an adapted version of [4], is inspired by the work of [5] and [6]. The work in the literature also attempts to identify the implicit aspect words i.e., aspects that are not mentioned directly, unlike the explicit aspects which are mentioned literally in [1].The above would not have been able to identify the 'anecdotes/miscellaneous' type of aspects because they were not directly mentioned in a sentence.…”

Section: Literature Reviewmentioning

confidence: 99%

A comprehensive survey of research based on extraction of opinion words and opinion targets from customer reviews

Kaur¹,

Bandyopadhyay²,

Sowmiya³

2018

IJET

View full text Add to dashboard Cite

This survey paper categorizes, compares, and summarizes the algorithms, data sets and performance measurement in the published articles related to extraction of opinion targets and words from customer reviews. The systems reviewed either deploy a supervised or completely unsupervised algorithm for the process. Most of the systems rely on K-nearest neighbor algorithm or a bootstrapping approach. Most of the methods have produced a list comprising of opinion targets from the customer reviews of a product. As a result, opinion targets usually are product features or attributes. The approaches mentioned in the papers reviewed suffer either from error propagation or from lack of automation for parsing long span relations. Certain approaches have taken an initial bag of seed words and proceeded to exploit the syntactical relationship between opinion words and targets. Mainly online product reviews have been used. It is generally believed that the co-occurrence of certain target and opinion words in close proximity makes them more relevant to each other and to the product as well. Owing to the nature of online review data sets most literature have not include assessment of opinion targets and words across multiple domains.

show abstract

“…At this purpose, we consider that a TRS is mature, if a number of credibility aspects and criteria are verified by the System's approach. To gather these trustworthiness aspects, we have focused on more recent surveys on the TRS as well as novel TRS works such as [1,3,4] published in 2007, [5,6,7] in 2010, [8,9,10] in 2013, [11,12,13] in 2013, and [14, 15,16] in 2015. The most relevant trustworthiness aspects that are the most used in the state of the art of the TRS are related to the reviewing and the rating process adopted in the TRS analysis.…”

Section: Introductionmentioning

confidence: 99%

State of the art of Trust and Reputation Systems in E-Commerce Context

Rahimi¹,

Bakkali²

2017

IJCSI

View full text Add to dashboard Cite

This article proposes in depth comparative study of the most popular, used and analyzed Trust and Reputation System (TRS) according to the trust and reputation literature and in terms of specific trustworthiness criteria. This survey is realized relying on a selection of trustworthiness criteria that analyze and evaluate the maturity and effectiveness of TRS. These criteria describe the utility, the usability, the performance and the effectiveness of the TRS. We also provide a summary table of the compared TRS within a detailed and granular selection of trust and reputation aspects.

show abstract

Extracting implicit features in online customer reviews for opinion mining

Cited by 49 publications

References 4 publications

Finding Implicit Features in Consumer Reviews for Sentiment Analysis

Finding Implicit Features in Consumer Reviews for Sentiment Analysis

A comprehensive survey of research based on extraction of opinion words and opinion targets from customer reviews

State of the art of Trust and Reputation Systems in E-Commerce Context

Contact Info

Product

Resources

About