Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

The accessibility to large amount of datasets in commercial domains has accentuated the importance of data mining in the last few years. Practitioners as well as researchers rely on them to reflect on the magnitude and effect of data-related problems that require solution in business environments. In recent years, the volume of online data submissions (e-commerce data) on products, services and organizations has increased exponentially. However, the submitted data are highly unstructured and largely dependent on language. Mining and extracting useful information from such data is a colossal task, as analysis of the data should include opinion word identification/extraction, aspect extraction and entity extraction. Of the three, the entity extraction is one of the governing approaches in text analysis and plays a major role in e-commerce, biomedical and automobile industries and supports the categorization of the records based on the entity names, generation of short summary on the entities and grouping of the similar records. The existing approaches in entity extraction are capable of recognizing and extracting single-word named entities. However, the product names are often given as a sequence of words (multiple words or multi-word named entities) and, therefore, cannot be recognized by the existing methods. To resolve this issue, this paper presents a novel approach of NLP-Modified Token-based Frequencies of Left and Right (NLP-MTFLR), which is considered as an effective approach to detect and extract the multi-word named products and dominant multi-word named product from the customer review corpus. Using this NLP-MTFLR approach, from the review corpus the subwords and multi-subwords are identified and mapped them with its multi-word named products to recognize dominant product of that corpus. With this dominant product identification, the proposed method reveals in that corpus that the identified dominant product is highly reviewed by the reviewers compared to other products. This NLP-MTFLR approach is achieved 97% accuracy, 77% precision, 89% recall and 82% F-score. © 2017, King Fahd University of Petroleum &amp; Minerals.

Department of Smart Computing

School of Information Technology and Engineering

Vellore Campus

Department of Software and Systems Engineering

Arabian Journal for Science and Engineering

NLP-MTFLR: Document-Level Prioritization and Identification of Dominant Multi-word Named Products in Customer Reviews

Entity Extraction or product name extraction is a suitable premise for sentiment analysis. A sentiment discovers opinion of the customers on the product stated in the sentence. Extracting product names using the existing approaches from the customer’s reviews are not exact most of the time. Almost many existing approaches mainly lack in addressing the product name having multiple words or sequence of words (multi-word). When compared with single word named products, extracting opinion on multi-word named products are non-trivial task as customer use either full name or part of the product name (sub-word) in product reviews. Therefore, it is the foremost challenging task in sentiment analysis to recognize appropriate complete name of a specific product using the sub-word names. Secondly, the multi-word named products or sub-word named products may occur anywhere in the review sentences, the position of the product names cannot be predicted in advance. It may occur in the beginning, middle or at the end and also with any number of times. So, identifying the position of these product names is another key issue. Therefore, this research attempt to design a novel automated improved Context Information Weight (iCIW) approach to resolve the exiting issues. The iCIW assimilates the concept of lexicon and statistical approach. The proposed iCIW model is more suitable for document analysis related to medical reports, product details repository and political documents. The experimental result reveals that the proposed method performs very efficient than existing approaches in multi-word named product extraction. © School of Engineering, Taylor’s University.

Journal of Engineering Science and Technology

An empirical machine learning approach to extract and rank multi-word product names using iCIW approach

The term “Entity Extraction” is a renowned technique now and broadly employed as a part of opinion mining and sentiment analysis. This technique is one of the information retrieval approaches, where the precise data have been obtained from the huge volume of information resources. Entity extraction is a traditional approach of named entity extraction, which is basically, retrieves the person name, product names, organization names, services, political issues titles, news article titles, locations and local and global time and etc. This entity extraction is very interesting filed and plays a major role in bio-medical field to recognize the drug entities, understand biological data in bioinformatics and categorize bio-medical documents, document summarization and explore the bio-medical terms and etc. Since the volume of online data has been increasing day by day, the entity extraction process needs more efficient techniques to find the entity replication, document replication, semantics between entities and documents and etc. This paper presents a study of various approaches employed in entity extraction on unstructured data. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

A literature survey on entity extraction techniques in bio-medical datasets

In recent years, the volume of data submissions (E-Commerce data) in online on products, service, and organizations is increasing exponentially. This online data is abundantly unstructured; extracting knowledge from that huge volume of data is a non-trivial task. In recent years, extracting product names become a very popular approach and also one of the important methods in sentiment analysis. This product name extraction is very useful in E-commerce, because it helps in identifying people interest on products, generation of reviews' metadata and identification of product attributes, etc. The existing approaches in product name extraction are capable of extracting single word product names. However, the product names can be a sequence of words, which is also called multi-word product names that cannot be obtained automatically by the existing methods. In this paper, a combined approach of semi-supervised machine learning and improved C-value approach is proposed to discover the multi-word product names, ranking those product names and identifying a dominant product in review documents.

2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

An empirical semi-supervised machine learning approach on extracting and ranking document level multi-word product names using improved C-value approach

A Proxy signature scheme enables a proxy signer to sign a message on behalf of the original signer. In this paper, we propose efficient and secure Proxy multi-signature scheme based on elliptic curve cryptosystem. Our scheme satisfy all the proxy requirements and require only elliptic curve multiplication and elliptic curve addition which needs less computation overhead compared to modular exponentiation also our scheme is withstand against original signer forgery and public key substitution attack. © 2012 Springer-Verlag.