Big data sentiment analysis using distributed computing approach

Abstract

Big data refers to three properties, namely, volume, variety, and velocity. Big data is used because of its huge storage capacity, high processing power, and availability of data. Big data is used now due to its availability of powerful multi-core processors, possibility of low latency by distributed computing, partitioning—aggregating—isolating resources in any size and hot swapping dynamically, affordable storage, and computing with minimal man power with the help of cloud deployment models. Sentiment analysis is one of the data mining techniques that is used for measuring users sentiments through techniques like natural language processing (NLP), computational linguistics, digital technology, artificial intelligence, and text analysis. These techniques are used for identifying, extracting, and analyzing subjective information from multiple Web sources. The sentiment analysis explores the contextual divergence of the information/data. Every day, different varieties of data are generating in volumes with high velocity, typically in multiples of 1024 bytes, which means from a petabyte to exabyte. Users around the globe are sharing/communicating/exchanging huge bytes of data through the medium of different sources like social sites, e-commerce sites, file sharing, database repositories, and secondary storage devices. These huge bytes of data may be structured, unstructured, and semi-structured. Analyzing such vast voluminous and veracity of data plays a crucial role in knowing customer behavior and thoughts. Data analytics also known as data analysis refers to qualitative and quantitative techniques and processes used to enhance productivity and business gain. Data is extracted and categorized to identify and analyze behavioral data and patterns, and techniques vary according to organizational requirements. During sentiment analysis process, the data analyst is able to extract a best solution based on sentiment variation and fantasy analysis of a user. This solution could be used for enhancement of business/organization/product/or services, etc. In this work, we are analyzing social data using sentiment analysis, which checks the attitude of user interests, using distributed computing approach, to result in an effective solution.