An Effective Undesired Content Filtration and Predictions Framework in Online Social Network

<span lang="EN-US">Currently, customer's product review opinion plays an essential role in deciding the purchasing of the online product. A customer prefers to acquire the opinion of other customers by viewing their opinion during online products' reviews, blogs and social networking sites, etc. The majority of the product reviews including huge words. A few users provide the opinion; it is tough to analysis and understands the meaning of reviews. To improve user fulfillment and shopping experience, it has become a general practice for online sellers to allow their users to review or to communicate opinions of the products that they have sold. The major goal of the paper is to solve feature extraction problem and opinion classification problem from customers utilized product reviews which extract the feature words and opinion words from product reviews. To propose an Efficient Feature Extraction and Classification (EFEC) algorithm is implementing to extracts a feature from opinion words. The reviewer usually marks both positive and negative parts of the reviewed product, despite the fact that their general opinion on the product may be positive or negative. An EFEC algorithm is utilized to predict the number of positive and negative opinion in reviews. Based on Experimental evaluations, proposed algorithm improves accuracy 15.05%, precision 13.7%, recall 15.59% and F-measure 15.07% of the proposed system compared than existing methodologies</span>

Section: Introductionmentioning

confidence: 99%

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

Solainayagi¹,

Ponnusamy²

2018

“…The device aims to improve the quality of life for the blind and visually impaired people and makes them understand their surroundings in a clear way as close as to a normal person at affordable costs. Prakash et al [10] implemented an approximation automated structure, called Filtered Wall (FW) and it filtered disposed of substance from OSN client substances. The goal is to utilize efficient classification procedure to stay away from overpowered by unsuccessful messages.…”

Section: Introductionmentioning

confidence: 99%

Fabricating Modish Mobile Application for a Visionless Citizen to Act as a Visioned Citizen

Jananee¹,

Shalini²,

Dhivya³

2018

<p>Technology has its wide range of applications in every field potentially even on the Mobile technology. One of the technologies which accomplish the blind person in android mobile is Virtual Reality. In spite of virtual reality is engaged to effectuate the operations, the blind person attention is one of the most important statistics. Although mobile devices include operative features available for amaurotic users, the user interface of the greater part of the mobile apps is designed for sighted people. If they carry out any mistakes to use the apps it may lead to a wrong call. So, one may think of a technology that diminishes the anxiety of a blind person for using apps. The proposed system converts the text into audio for giving the directions to the blind person about the gestures inferred. For such conversion a technique called speech synthesizer is used. Assorted innovative tools are used in mobile phones. Blind people need to confide in normal person for creating and updating a contact. Our project incorporates the gestures from the blind people and confirms the gestures through voice. Gesture conversion is accomplished by using haptic technology. An amaurotic person can create a new contact and they can invoke the contact by using this voice confirmation. During calling if there is multiple contact list, caller setting are initialized and ask the preference from the blind people, progress the voice call.</p>

“…It also defined a set of properties for profile attributes-Availability, Consistency, non-Impressionability, and Discriminability (ACID)-that are both necessary and sufficient to determine the reliability of a matching scheme. Sun et al [3] [4] implemented an approximation automated structure, called Filtered Wall (FW) and it filtered disposed of substance from OSN client substances. The goal is to utilize efficient classification procedure to stay away from overpowered by unsuccessful messages.…”

Section: Introductionmentioning

confidence: 99%

Selective Colligation and Selective Scrambling for Privacy Preservation in Data Mining

Ishwarya¹,

Kumar²

2018

The work is to enhance the time efficiency in retrieving the data from enormous bank database. The major drawback in retrieving data from large databases is time delay. This time hindrance is owed as the already existing method (SVM), Abstract Data Type (ADT) tree pursues some elongated Sequential steps. These techniques takes additional size and with a reduction of speed in training and testing. Another major negative aspect of these techniques is its Algorithmic complexity. The classification algorithms have five categories. They are ID3, k-nearest neighbour, Decision tree, ANN, and Naïve Bayes algorithm. To triumph over the drawbacks in SVM techniques, we worn a technique called Naïve Bayes Classification (NBC) Algorithm that works in parallel manner rather than sequential manner. For further enhancement we commenced a Naïve Bayes updatable algorithm which is the advanced version of Naïve Bayes classification algorithm. Thus the proposed technique Naïve bayes algorithm ensures that miner can mine more efficiently from the enormous database.