Amitt Sharma

This is a documentation of our approach in building a completely automated sentiment analysis software that helps manufacturers as well as customers in making sense of the huge amount of user reviews available across e-commerce websites, and for any product category, in real-time.

-Scans every line of data, and generates a cogent aggregated summary, across various dimensions like features, frequency and time, along with intuitive visualizations. The system takes into account the holistic… Show more

This is a documentation of our approach in building a completely automated sentiment analysis software that helps manufacturers as well as customers in making sense of the huge amount of user reviews available across e-commerce websites, and for any product category, in real-time.

-Scans every line of data, and generates a cogent aggregated summary, across various dimensions like features, frequency and time, along with intuitive visualizations. The system takes into account the holistic sentiment and breaks down each review to analyse the sentiment corresponding to relevant features, and then calculates the overall sentiment in a bottom-up fashion.

-Employs a self-learning mechanism that identifies what exactly the searched keyword refers to and what its characteristics/features should be. It continues to aggregate more features into its list for the same category. So, the hit ratio of the system increases as it progresses.

-Works across varied domains like Electronics (further includes Refrigerators, Mobile Phones etc), Lifestyle, Home and Kitchen utilities etc Show less

This paper presents an approach for monitoring Facebook posts and comments in real-time, with an aim at identifying plausible riots that could spur up as a result. In this research, we employ an NLP and sentiment analysis based algorithm to classify a discussion as likely to cause a riot or not and identify the power groups involved in it.

We regularly use communication apps like Facebook and WhatsApp on our smartphones, and the exchange of media, particularly images, has grown at an exponential rate. There are over 3 billion images shared every day on Whatsapp alone. In such a scenario, the management of images on a mobile device has become highly inefficient, and this leads to problems like low storage, manual deletion of images, disorganization etc. In this paper, we present a solution to tackle these issues by automatically… Show more

We regularly use communication apps like Facebook and WhatsApp on our smartphones, and the exchange of media, particularly images, has grown at an exponential rate. There are over 3 billion images shared every day on Whatsapp alone. In such a scenario, the management of images on a mobile device has become highly inefficient, and this leads to problems like low storage, manual deletion of images, disorganization etc. In this paper, we present a solution to tackle these issues by automatically classifying every image on a smartphone into a set of predefined categories, thereby segregating spam images from them, allowing the user to delete them seamlessly. Show less

With the dawn of the information age, knowledge discovery and exchange is increasing exponentially every day and a new paradigm in education has emerged which is the Massive open online courses or MOOCs. Our research aims at exploring the fundamentals that gives MOOCs an edge over the traditional courses and highlights the weakness of MOOCs over traditional courses. In our study we present a statistical analysis of the hypotheses developed to understand the fundamentals of MOOCs and reasons for… Show more

With the dawn of the information age, knowledge discovery and exchange is increasing exponentially every day and a new paradigm in education has emerged which is the Massive open online courses or MOOCs. Our research aims at exploring the fundamentals that gives MOOCs an edge over the traditional courses and highlights the weakness of MOOCs over traditional courses. In our study we present a statistical analysis of the hypotheses developed to understand the fundamentals of MOOCs and reasons for the huge dropout rates. Based on these empirical evidences we also propose ways to decrease the attrition rates. Show less