International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 02 | Feb -2017
p-ISSN: 2395-0072
www.irjet.net
Efficiently Detecting and Analyzing Spam Reviews Using Live Data Feed Jyoti N. Nandimath1, Bhavesh S. Katkar2, Vikram U. Ghadge3, Arjun N. Garad4 1Professor,
Dept. of Computer Engineering, SKNCOE Pune, Maharashtra, India Dept. of Computer Engineering, SKNCOE Pune, Maharashtra, India 3Student, Dept. of Computer Engineering, SKNCOE Pune, Maharashtra, India 4Student, Dept. of Computer Engineering, SKNCOE Pune, Maharashtra, India 2Student,
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In recent year, online reviews have become the
sentiment analysis involve opinion integration algorithm, connecting opinion analyzing algorithm, etc. This paper focuses on opinion integration algorithm, and actualizes a comment fake as well as spam detection system, based on evidence classifier. As it is said before, the development of the Internet promotes the development of economy and technology; online shopping is getting more and more popular. While making their final decisions, users tend to rely on the online comments. However, some information, which is posted on purpose, not according to the fact, is useless for users. So these comments should be regarded as spam. If they are not detected and deleted on time, they may waste the users precious time of making their decisions. A nice way to solve this problem is to establish an opinion spam detection system.
most important resource of customer opinion. Existing research has been focused used on extraction, classification and summarization of opinion from reviews in websites, forums and blogs. Now-a-days consumer can obtain information for products and service from online review resources, which can help them make decision. The social tools provided by the content sharing applications allow online user to interact, to express their opinions and to read opinions from other users. But the spammers provide comments which are written intentionally to mislead users by redirecting them to web sites to increase their rating and to promote products less known on the market. Reading spam comments is a bad experience and a waste of time for most of the online users but can also be harming and cause damage to the reader. Several researchers in this field focused on only fake comments. But, our goal is to detect fake comments which are likely to represent spam considering some indicators like a discontinuous own of text, inadequate and vulgar language or not related to the specific context will helps in giving correct feedback of various customers reviews about given product ,Mainly we have observed that previous work is focused on extraction, classification and summarization of opinion and checking of spam and non-spam. But, proposed system aims to Evaluate genuine result of filter comments ,so that business analyst can make the decision for their organization.
2. LITERATURE REVIEW The increase in the data rates generated on the digital universe is escalating exponentially. With a view in employing current tools and technologies to analyze and store, a massive volume of data are not up to the mark, since they are unable to extract required sample data sets. Therefore, we must design an architectural platform for analyzing both remote access real time and offline data. When a business enterprise can pull-out all the useful information obtainable in the Big Data rather than a sample of its data set, in that case, it has an influential benefit over the market competitors. Big Data analytics helps us to gain insight and make better decisions. To support our motivations, we have described some areas where Big Data can play an important role.
Key Words:
Distributed Computing, Cloud Computing, Server, Sentiment Analysis and Python.
1.INTRODUCTION Nowadays, the Internet contains a vast amount of text messages, and these messages need to be deeply analyzed and well estimated. Opinion mining now newly became one of the most heated areas in computer science. At the same time, electronic commerce, also known as ecommerce, is shooting up, which leads to a fast growth in the amount of users comments. And, the users comments do influence other buyers final choice. Therefore, making a good use of the comments will actualize their practical use. The process of opinion mining could be on the level of the texts, and the sentences as well. Opinion mining and
Š 2017, IRJET
|
Impact Factor value: 5.181
In healthcare scenarios, medical practitioners gather massive volume of data about patients, medical history, medications, and other details. The above-mentioned data are accumulated in drug-manufacturing companies. The nature of these data is very complex, and sometimes the practitioners are unable to show a relationship with other information, which results in missing of important
|
ISO 9001:2008 Certified Journal
|
Page 1421