Sentiment analysis of movie reviews: A new feature-based heuristic for aspect-level sentiment classification

Singh, Vivek Kumar; Piryani, Rajesh; Uddin, Ashraf; Waila, P.

doi:10.1109/imac4s.2013.6526500

Cited by 156 publications

(62 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We chose to employ a publicly available tool, AlchemyAPI [1], for this purpose. AlchemyAPI is known to present high accuracy on identification of sentiments in various applications including reviews and tweets [14,16], which gives us good confidence in using the API.…”

Section: Stage 2: Sentiment Analysis On User Relationshipsmentioning

confidence: 99%

Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

Choo

Chi

2015

Data and Applications Security and Privacy XXIX

View full text Add to dashboard Cite

Abstract. In this paper we investigate on detection of opinion spammer groups in review systems. Most existing approaches typically build pure content-based classifiers, using various features extracted from review contents; however, spammers can superficially alter their review contents to avoid detections. In our approach, we focus on user relationships built through interactions to identify spammers. Previously, we revealed the existence of implicit communities among users based upon their interaction patterns [3]. In this work we further explore the community structures to distinguish spam communities from non-spam ones with sentiment analysis on user interactions. Through extensive experiments over a dataset collected from Amazon, we found that the discovered strong positive communities are more likely to be opinion spammer groups. In fact, our results show that our approach is comparable to the existing state-of-art content-based classifier, meaning that our approach can identify spammer groups reliably even if spammers alter their contents.

show abstract

Section: Stage 2: Sentiment Analysis On User Relationshipsmentioning

confidence: 99%

Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

Choo

Chi

2015

Data and Applications Security and Privacy XXIX

View full text Add to dashboard Cite

show abstract

“…So using SentiWordNet [2] we have analyzed the sentiments of the feedbacks given by various users. Also the user is supposed to give rating.…”

Section: IVmentioning

confidence: 99%

Building Trustworthiness of UserFeedbacks on Products in Online Shopping Environment

Thakkar¹

2015

IJRITCC

View full text Add to dashboard Cite

Lack of Trust is the main issue why people fear using E-Commerce for their regular shopping purpose, whereas E-Commerce is very much cost-effective as compared to traditional shopping. But people fear using E-Commerce just because there is no personal contact with the vendor. So it is a biggest challenge to remove this fear from the minds of buyers. The only solution to remove this fear is building Trust in their minds. There are many factors which should be focussed upon while building this trust, they are broadly classified as Knowledge-Based Trust which includes familiarity, reputation, brand, size, website quality, and customer service. We in this thesis have considered reputation as a factor to enhance the website quality. In our implementation we make sure that users give genuine feedbacks on the products. We use the concept of Sentiment Analysis to know the sentiment behind the given semantic feedback and check its concordance with rating given by the same user. If concordance is satisfactory user has to like or dislike five prefabricated feedbacks. Using both the concordance and like-dislike results, Trust Degree of the user is calculated. If the Trust Degree is above certain threshold then the feedback of that user is submitted to our website else the user is blocked. This is how we improve website quality by our implementation.

show abstract

“…g) Sentiment Analysis [2][10] is done on the reviews to give user an opinion whether to buy product or not.…”

Section: IImentioning

confidence: 99%

Trustworthiness and Analysis of Sentiment of user�s Semantic Feedbacks in E-Commerce

Thakkar¹,

Vora²

2015

IJRITCC

View full text Add to dashboard Cite

-While Shopping Online Buyers mostly depend on reviews from users available on various websites. Trust is an important factor in any sort of relationship. A buyer can often see both the seller and the product, verify its quality, negotiate and bargain with the seller in traditional commerce. But in the context of online shopping, there is a absence of this face to face trust assessment. Absence of trust is always considered as an hurdle in online transactions. Ratings are available online. However those ratings are not always truthful. Then, they can falsify the weight and the scores .Semantic feedbacks make more sense than single scores. Our System aims at creating trust in online communities while giving action taking results .Those results such as trust weight, scores and the results of Sentiment Analysis help users to make a decision about purchasing particular product or not from an e-commerce application. Proposed design will use both ratings and semantic feedbacks to calculate trust weight and to classify comments and users.

show abstract

Sentiment analysis of movie reviews: A new feature-based heuristic for aspect-level sentiment classification

Cited by 156 publications

References 6 publications

Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

Building Trustworthiness of UserFeedbacks on Products in Online Shopping Environment

Trustworthiness and Analysis of Sentiment of user�s Semantic Feedbacks in E-Commerce

Contact Info

Product

Resources

About