Opinion Mining on Social Media Data

Liang, Po‐Wei; Dai, Bi-Ru

doi:10.1109/mdm.2013.73

Cited by 88 publications

(43 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Proposed hybrid Partical Swarm Optimization (PSO) is used to improve the election of best parameter in order to solve the dual optimization problem. Po-Wei Liang and Bi-Ru Dai [4] proposed a method for opinion mining on social media data. In their paper, they proposed a new system architecture that can automatically examine the sentiments of these messages.…”

Section: Literature Surveymentioning

confidence: 99%

Effective Product Ranking Method based on Opinion Mining

Kulkarni¹,

Lingayat²

2015

IJCA

View full text Add to dashboard Cite

As internet is spreading out its bound, the demand of online transaction is also getting considerably increased. Now everyone wants fast and direct to home service without tacking any efforts. Online shopping is a way of effective transaction between money and goods which is done by end user without spending a large time span. Every product on online shopping website is associated with reviews which represents quality of that particular product. Every time the consumers are purchasing the product online by reading the product review. But reading all these reviews before buying product, consumes more time. Hence there is need of some systematic analysis of product reviews which helps to the consumer to find effective product among millions of the products. Here we have proposed a novel approach to rank the product efficiently by mining the genuine reviews of the product. But major problem arises when there is assignment of fake review given by anonymous user. So this system will provide methodology which will allow only those users to give review who have purchased product from that website. Other users are not allowed to give review. This will reduce the wrong reviewing of product and customer will get reliable product.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Effective Product Ranking Method based on Opinion Mining

Kulkarni¹,

Lingayat²

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…and Dai, B.-R. [12] design a system called opinion miner which integrated machine learning techniques and domain-specific data. They used unigram Naïve Bayes for extracting tweets and determined that is an opinion or not.…”

Section: Related Workmentioning

confidence: 99%

Measuring Opinion Credibility in Twitter

Thandar

Usanavasin

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

sentiment analyzer and opinion credibility calculator. We use two machine learning techniques: Naïve Bayes (NB) and Support Vector Machine (SVM) for sentiment analyzer. To define expert knowledge, we use author's profile, list features and author's tweets behaviour for weight factors in twitter. In opinion calculator, we produce opinion credibility value combine with sentiment analyzer result and expert knowledge score.Thereafter we converse all of our defined author's expert weight factors to analyses which weight factors weightier than others and which factors can support more credible when we compute opinion credibility. To evaluate our method we used weighted kappa statistic for accuracy of opinion credibility.

show abstract

“…Twitter was created as a microblogging website in March of the year 2006 and formallyinitiated in July of the same year by Jack Dorsey, Evan Williams, Biz Stone and Noah Glas (Mosley and Roosevelt, 2012). Twitter is considered to be one of the widelyprevalent micro-blogging platforms in which users are able to generate status messages called "tweets", which are status updates and musings that cannot exceed 140 characters (Liang and Dai, 2013). These messages are broadcasted to a global audience (Conover et al, 2011).…”

Section: Twittermentioning

confidence: 99%

“…This is an indication of good similarity between users (Goyal, 2011). Since the majority of the user-generated messages on micro-blogging websites are textual information (Liang and Dai, 2013); therefore, the main focus of this study is clustering of tweets based on their textual content similarity. Since English is the most commonly used language in Twitter (Honey and Herring, 2009), the focus is on tweets written in English.…”

Section: The Problemmentioning

confidence: 99%

Clustering Tweets Using Cellular Genetic Algorithm

Adel¹

2014

Journal of Computer Science

View full text Add to dashboard Cite

As the popularity of Twitter continues to increase rapidly, it is extremely necessary to analyze the huge amount of data that Twitter users generate. A popular method of tweet analysis is clustering. Because most tweets are textual, this study focuses on clustering tweets based on their textual content similarity. This study presents tweet clustering using cellular genetic algorithm cGA. The results obtained by cGA are compared with those obtained by generational genetic algorithm in terms of average fitness, average time required for execution and number of generations. Experimental results are tested with two sets: One of 1000 tweets and the second formed of 5000 tweets. The results show a nearly equal performance for both algorithms in terms of the average fitness of the solution. On the other hand, cGA shows a much faster performance than generational. These results demonstrate that cellular genetic algorithm outperforms generational genetic algorithm in tweet clustering.

show abstract

Opinion Mining on Social Media Data

Cited by 88 publications

References 9 publications

Effective Product Ranking Method based on Opinion Mining

Effective Product Ranking Method based on Opinion Mining

Measuring Opinion Credibility in Twitter

Clustering Tweets Using Cellular Genetic Algorithm

Contact Info

Product

Resources

About