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

Polarity detection is an emerging area of research in text mining. Polarity detection is observing and identifying the sentiment inclination of text, whether it is positive or negative. In this paper, a fast mode of supervised learning for polarity detection on tweets is proposed, that is using datasets available in public. The feature selection strategy ensures reduced dimensionality. The low dimension data processing on Apache Spark supports scalability for large datasets. The experiment shows that the method is supporting high scalability and efficiency. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021

Department of Computational Intelligence

School of Computer Science and Engineering

Vellore Campus

World University root node

Lecture Notes in Networks and Systems

A Fast Mode of Tweets Polarity Detection

Sentiment analysis is an interesting area of research due to the availability of sentiment data and opinion-oriented services. The efficiency and scalability of the sentiment analysis applications are important concerns as they expect accurate results in short period of time by processing a large amount of data. An efficient and scalable polarity detection method is proposed in this paper. The sequential minimal optimization with MapReduce (SMOMR) is used to achieve enhanced efficiency as well as scalability. The experiment results reveal that this method outperforms many existing methods. © 2020, Springer Nature Singapore Pte Ltd.

Advances in Intelligent Systems and Computing

A Large-Scale Implementation Using MapReduce-Based SVM for Tweets Sentiment Analysis

Nowadays, Internet-based data classification and interpretation applications are very popular. Those applications automatically detect the information in text and classify it in various classes based on the users’ requirements. Those commercial applications require immediate results for satisfying their costumers and succeed competitors. This paper presents a model that detects the polarity of the tweets in a very efficient manner. In the proposed model, Apache Spark supports scalability for large data sets and the supervised learning is ensuring efficiency. The experiment shows that the proposed method’s performance is better than the Naïve Bayes, SVM, etc. © 2019, Institute of Advanced Scientific Research, Inc.. All rights reserved.

VIT Unitversity

Journal of Advanced Research in Dynamical and Control Systems

A Distributed Approach for Tweet Polarity Detection

Big Data refers to the extremely big datasets that are produced from different areas which exhibits certain trends and associations. Major areas of big data include medical data, sensor data, social networks such as facebook, twitter, youtube etc. Among this, social networks produce large amount of data per millisecond which can be analysed for several predictive and analytic purposes. Tweets produced by twitter is used in sentiment analysis and polarity detection that helps in identifying the attitude, polarity of words, text or documents. Applying polarity detection in big data is a tedious task as it includes both historical and streaming data. Several frameworks have been proposed for analysing both historical and streaming data in big data. In this paper, lambda architecture for polarity detection of tweets has been proposed which analyses both streaming and historical data. Both the data can be analysed in parallel and used for certain predictive and analytic purposes. © 2019 IEEE.

2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)

A Big Data Processing Framework for Polarity Detection in Social Network Data

Protein–protein interactions (PPIs) play vital roles in various cellular pathways. Most of the proteins perform their responsibilities by interacting with an enormous number of proteins. Understanding these interactions of the proteins and their interacting partners has shed light toward the field of drug discovery. Also, PPIs enable us to understand the functions of a protein by understanding their interacting partners. Consequently, in the current study, PPI network of the proteins causing MODY (Maturity Onset Diabetes of the Young) was drawn, and their correlation in causing a disease condition was marked. MODY is a monogenic type of diabetes caused by autosomal dominant inheritance. Extensive research on transcription factor and their corresponding genetic pathways have been studied over the last three decades, yet, very little is understood about the molecular modalities of highly dynamic interactions between transcription factors, genomic DNA, and the protein partners. The current study also reveals the interacting patterns of the various transcription factors. Consequently, in the current work, we have devised a PPI analysis to understand the plausible pathway through which the protein leads to a deformity in glucose uptake. © 2018 Elsevier Inc.

Department of Integrative Biology

School of Bio Sciences and Technology

Department of Biotechnology

Protein-Protein Interactions in Human Disease, Part A Advances in Protein Chemistry and Structural Biology

Probing the Protein–Protein Interaction Network of Proteins Causing Maturity Onset Diabetes of the Young

Big Data are a large amount of data that are being generated from social networks, mobile devices, sensors, etc. It was a great challenge to store and process Big Data before the advent of Hadoop. Understanding Big Data drives the growth of any company (White, 2015). This is now possible with Hadoop. Hadoop is a set of libraries that provide methods to access and analyze these data in a fast and efficient manner. There are many flavors of Hadoop available to us. Apache Hadoop is open source, and a lot of projects have been developed surrounding Apache Hadoop (Lam, 2010). Cloudera Hadoop is also available as. © 2017 by Taylor and Francis Group, LLC.

Department of Software Systems

Department of Information Technology

School of Information Technology and Engineering

Department of Analytics

NoSQL: Database for Storage and Retrieval of Data in Cloud

In Scientific field, the data collection resulted into large scale growth by continuous additions of data. The characteristics such as velocity, variety, volume, etc. make the collected data as Big data. Analysis of such data uses various data mining techniques. Clustering is one among them and it is an unsupervised learning technique used for statistical data in bioinformatics, social networks, etc. Among various clustering techniques the K -means clustering is a common and predominant algorithm. However, the accuracy of original K-means algorithm heavily depends on centroids at the beginning and it has high computational complexity. In this paper we present an empirical study on enhanced k-means algorithm for high accuracy clustering with the initial centroids selection in an improved manner. © Research India Publications.

Department of Information Security

International Journal of Applied Engineering Research

Case study on enhanced K-means algorithm for bioinformatics data clustering

Online reviews become one of the primary factors in many decision making situations. There is a possibility to impact the business negatively or positively. In this work, review centric features and the reviewer centric features will be considered for feature selection. Reviewer centric features give a comprehensive aspect of the reviews. These features will give the information about that particular author. Rather than information about the text content, review centric feature will give information about the reviews. One of the machine learning technique; supervised learning is used to detect the spam in reviews. This is implemented using Hadoop architecture. HDFS is used to store the data set. Analysis and model building will be doing with the help of open source software H2O. © 2017 IEEE.

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI)

Opinion spam detection using review and reviewer centric features

The impact of the social networks-based sentiment analysis (SA) and opinion mining has increased in recent times. Decision-makers consider the opinions of the thought leaders and laymen, and plenty of opinions are available in social networks. When a user wants to get a service or buy a product he or she will check for the reviews and opinions provided by other people about various offerings. Opinion rich data sources are available in digital form; this attracts many researchers to focus research on SA. The 'sentiments' available in social networks and review pages are highly valuable for industries and individuals who want to closely monitor their reputation and live feedback about their services and products. This paper presents a review covering techniques, tools, data resources and applications in the area of textbased SA. Copyright © 2017 Inderscience Enterprises Ltd.

Fulltext

International Journal of Knowledge and Learning

Text-based sentiment analysis: review

Cloud computing allows much more efficient computing by centralizing storage, memory, procession and bandwidth. The data is stored in off-premises and accessing this data through keyword search. Traditional keyword search was based on plaintext keyword search. But for protecting data privacy the sensitive data should be encrypted before outsourcing. One of the most popular ways is selectively retrieve files through keyword-based search instead of retrieving all the encrypted files back. Present methods are focusing on the fuzzy keyword search and which efficiently search and retrieve the data in most secure and privacy preserved manner. The existing system uses single fuzzy keyword searching mechanism. A conjunctive/sequence of keyword search mechanism will retrieve most efficient and relevant data files. The conjunctive/sequence of keyword search automatically generates ranked results so that the searching flexibility and efficiency will be improved. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.

Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering

Improving the efficiency of data retrieval in secure cloud

Recently, the most announced word in the world of computation is 'Cloud Computing'. In cloud computing, the services are provided by some vendors and the customers are unaware about the storage and maintenance of their data. So, logically speaking, the client has no control over the cloud. When the service providers process the data being provided by the customers, issues like privacy loss and data leakage may arise. This is an important barrier for the adoption of cloud services. A user-centric approach is essential to overcome this barrier. In this paper we present a solution which provides the control, over the data being submitted in the cloud, to the user. © Springer-Verlag 2011.