Jayakumar Sadhasivam

Bio: Jayakumar Sadhasivam is an academic researcher from VIT University. The author has contributed to research in topics: Genetic algorithm & Feature selection. The author has an hindex of 3, co-authored 10 publications receiving 25 citations.

Sentiment Analysis of Amazon Products Using Ensemble Machine Learning Algorithm

Abstract: In recent years, Sentimental Analysis is used in all online product firms. The number of users using the particular product has increased which makes the industry to improvise the characteristics of the product. These days, many users who are using websites, blogs, online shopping tends to review the products they used. These reviews were taken into consideration by other users during their search for products. Hence the industry has found the root of delivering the correct product searched by the user based on the reviews of the users using the concept of sentimental analysis. Sentimental Analysis is the concept of data analysis where the collections of reviews are taken into consideration, and those reviews are analyzed, processed and recommended to the user. The reviews given are longer and which consist of a few paragraphs of content. In this paper, the dataset is collected from the official product sites. Initially, these reviews must be pre-processed in order to remove the unwanted data’s such as stop words, be verbs, punctuations, and conjunctions. Once, the pre-processing is over the trained dataset is classified using Naive Bayes and SVM algorithm. These existing algorithms provided the accuracy which is not worth enough. Hence, an ensemble approach has been applied to enhance the accuracy of the given reviews. An ensemble is a classification approach by combining two or more algorithms and calculate the mode value based on the vote reference for every algorithm which is used. In this paper, Naive Bayes, SVM, and Ensemble algorithm are combined. We proposed an Ensemble method that helps in providing better accuracy than the current existing algorithm. Once the accuracy is calculated, based on the reviews, the particular product is recommended for the user.

Educational Paradigm Shift: Are We Ready to Adopt MOOC?

Abstract: This paper summarizes the findings from an empirical study carry out the online learning. The impact of information technology in our day-to-day life has been profound. Among many cross disciplines that have been enriched (or benefited) by information technology, educational media is not an exception. MOOC (Massive Open Online Courses brings learning, teaching and assessment. MOOC is a Web-based distance-learning program that is designed for the participation of large numbers of geographically dispersed students. In addition, Google and other companies are involving to design and fund to low-cost eLearning. Niche market provides nine certification courses via MOOC, to satisfy the employees specific needs. However, in the present day context the opinion on embracing MOOC by an University has been quite debatable. Addressing this debate on both sides, this papers presents the opinion expressed by the stakeholders in education towards embracing MOOC. Based on the findings from the study, the paper will discuss the challenge and broad concerns applicable to eLearning. The survey is focused on providing a consolidated fact that based on penetration of eLearning. This paper is aimed at providing a solid analysis of eLearning with the help of IT infrastructure in India. The survey contains demographic distribution of faculties; student and system administrator ratio is 39.6. Among a total of 792 of 2000 participants. It is focused that eLearning strategy in India.

Mooc: a framework for learners using learning style

Abstract: A modern problem of current societies is the excellence of their education structures. MOOCs are innovative devices that have been utilized to enhance and augment the traditional educational framework. MOOC is defined to have enormous profit by its technological advances. When an instructive stage is available and still there is a scope for components to give virtual instructive situations where each learner is viewed as a principle performer in the outline of the learning process, thereby adding to expand the quality of education. It is essential for the MOOCs providers to see if learning is more powerful when it is introduced through one methodology as opposed to another methodology. This is especially essential when working with understudies with particular learning challenges who frequently experience issues get to realize when it is just exhibited through their weaker methodology. What we should remember is that people are different, and each of us learn differently (1) . The very same learning conditions, guidance and instructions (2) that can be so effective for one person can cause problems for another (3) . The learning styles must be anticipated deliberately, in light of the fact that the mental equalization is variable in nature and the MOOC are differentiated in light of the learning design, environment, time and their state of mind. Since 1930 the term learning style has been broadly utilized in psychology and pedagogy. Specifically, MOOC more often need components for perceiving users' learning styles, which depict the way a learner procures and process data. In this plan, we adduce a framework for automated identification of learning styles in MOOC. A key objective of this system design is to furnish and understand the user learning styles in MOOC.

Feature-Level Rating System Using Customer Reviews and Review Votes

Abstract: This work studies how we can obtain feature-level ratings of the mobile products from the customer reviews and review votes to influence decision-making, both for new customers and manufacturers. Such a rating system gives a more comprehensive picture of the product than what a product-level rating system offers. While product-level ratings are too generic, feature-level ratings are particular; we exactly know what is good or bad about the product. There has always been a need to know which features fall short or are doing well according to the customer’s perception. It keeps both the manufacturer and the customer well-informed in the decisions to make in improving the product and buying, respectively. Different customers are interested in different features. Thus, feature-level ratings can make buying decisions personalized. We analyze the customer reviews collected on an online shopping site (Amazon) about various mobile products and the review votes. Explicitly, we carry out a feature-focused sentiment analysis for this purpose. Eventually, our analysis yields ratings to 108 features for 4000+ mobiles sold online. It helps in decision-making on how to improve the product (from the manufacturer’s perspective) and in making the personalized buying decisions (from the buyer’s perspective) a possibility. Our analysis has applications in recommender systems, consumer research, and so on.

It is time to MOOC and SPOC in the Gulf Region

Abstract: In this paper we will explain massive open online courses (MOOCs)-how they started, their targeted audience, and what services they provide- and demonstrate selected MOOC service providers that best suit the Arabian Gulf region. The record annual growth for MOOCs has made many respected institutions reconsider their educational strategies. Many elite universities have started to join the stream; others are expected to join very soon. In this paper we will focus on select MOOC providers that will help institutions or individual instructors ride the stream before it is too late. All MOOC providers have been carefully selected to meet the author’s criteria of either having crossed a capacity range limit or being tailored to meet the Arabian Gulf region needs. Finally, the paper summarizes the best practices and gives recommendations for any Gulf region institution or individual for better implementation of MOOCs into their learning system.

Evaluation of Sentiment Analysis via Word Embedding and RNN Variants for Amazon Online Reviews

Abstract: Consumer feedback is highly valuable in business to assess their performance and is also beneficial to customers as it gives them an idea of what to expect from new products. In this research, the aim is to evaluate different deep learning approaches to accurately predict the opinion of customers based on mobile phone reviews obtained from Amazon.com . The prediction is based on analysing these reviews and categorizing them as positive, negative, or neutral. Different deep learning algorithms have been implemented and evaluated such as simple RNN with its four variants, namely, Long Short-Term Memory Networks (LRNN), Group Long Short-Term Memory Networks (GLRNN), gated recurrent unit (GRNN), and update recurrent unit (UGRNN). All evaluated algorithms are combined with word embedding as feature extraction approach for sentiment analysis including Glove, word2vec, and FastText by Skip-grams. The five different algorithms with the three feature extraction methods are evaluated based on accuracy, recall, precision, and F1-score for both balanced and unbalanced datasets. For the unbalanced dataset, it was found that the GLRNN algorithms with FastText feature extraction scored the highest accuracy of 93.75%. This result achieved the highest accuracy on this dataset when compared with other methods mentioned in the literature. For the balanced dataset, the highest achieved accuracy was 88.39% by the LRNN algorithm.

E-Learning Recommender System for Learners: A Machine Learning based Approach

Abstract: Web mining procedure helps the surfers to get the required information but finding the exact information is as good as finding a needle in a haystack. In this work, an intelligent prediction model using Tensor Flow environment for Graphics Processing Unit (GPU) devices has been designed to meet the challenges of speed and accuracy. The proposed approach is isolated into two stages: pre-processing and prediction. In the first phase, the procedure starts via looking through the URLs of various e-learning sites particular to computer science subjects. At that point, the content of looked through URLs are perused and after that from their keywords are produced identified with a particular subject in the wake of playing out the pre-processing of the content. Second phase is prediction that predicts query specific links of e-learning website. The proposed Intelligent E-learning through Web (IEW) has content mining, lexical analysis, classification and machine learning based prediction as its key features. Algorithms like SVM, Naïve Bayes, K-Nearest Neighbor, and Random Forest were tested and it was found that Random Forest gave an accuracy of 98.98%, SVM 42%, KNN 63% and Naïve Bayes 66%. Based on the results IEW uses Random forest for prediction.

The role of massive open online courses during the COVID-19 era: Challenges and perspective

Abstract: The process of developing education is a vital and important issue around the world as it is an issue that is inherited through time, and it is one of the most important challenges facing the world. Distance education is one of the means of developing education through which knowledge can be spread and which can help people to overcome obstacles of time and space. Recently, teaching and learning systems have become completely dependent on e-learning, especially during the corona virus disease (COVID-19) pandemic since the world has turned to electronic transactions in all areas, especially in education, and the most used technology includes the use of online training courses such as massive open online courses (MOOCs). It provides great support to the distance learning process as it can facilitate the learning process by diversifying its contents via media, such as text and video. In addition, MOOCs are the most popular and effective online courses. The aim of this paper is to provide an in-depth analysis of the definition, characteristics and patterns of MOOCs. Also, this paper discusses the specific advantages and disadvantages of taking up MOOCs along with the different challenges that MOOCs are facing. In addition, various suggestions will be given to make improvements that can help in making process enhancements to MOOCs. Finally, this paper presents the importance of MOOCs in the COVID-19 era. We hope this paper will help instructors to understand how MOOCs can be made more efficient, enable learners to become more organised and increase their understanding of MOOCs, and will help education development system specialists to find suitable solutions for problems that MOOCs are facing. Keywords: Massive open online courses, e-learning, online courses, distance education, COVID-19.