I am passionate about Artificial Intelligence, Machine Learning, Statistics intrigue me and I love playing with numbers. Algorithms are what I love to design and giving solutions to people is what I believe in.
I'd like to be a solution provider rather than a scripter or another IT nerd who codes.
I love heavy metal, I love my nation and giving back to the society, I believe is the task of every engineer. I'd like to be that engineer. I love teaching and helping people since I am a firm believer that we learn more by helping others learn. Supervisors: Professor Uday Khedker Phone: +91 9762466450 Address: Pune, Maharashtra, India
The exponential increase in the use of the Internet and social media over the last two decades ha... more The exponential increase in the use of the Internet and social media over the last two decades has changed human interaction. This has led to many positive outcomes, but at the same time it has brought risks and harms. While the volume of harmful content online, such as hate speech, is not manageable by humans, interest in the academic community to investigate automated means for hate speech detection has increased. In this study, we analyse six publicly available datasets by combining them into a single homogeneous dataset and classify them into three classes, abusive, hateful or neither. We create a baseline model and we improve model performance scores using various optimisation techniques. After attaining a competitive performance score, we create a tool which identifies and scores a page with effective metric in near-real time and uses the same as feedback to re-train our model. We prove the competitive performance of our multilingual model on two langauges, English and Hindi, leading to comparable or superior performance to most monolingual models.
This paper explores the use of content-based and SVD filtering algorithm to increase the efficien... more This paper explores the use of content-based and SVD filtering algorithm to increase the efficiency and accuracy for a small subset of data-set. For mid-sized companies where data is scarce the existing algorithms for a recommendation system are futile. But Recommender systems have proven to be a valuable tool for web companies like Amazon and Netflix for attracting and maintaining a large user base as they have large dataset. Here in this paper we are using Yelp.com 1 data from a single city. We present the method to combine two approaches, and find that the MSE for predicting a user's new rating can be reduced from a baseline MSE of 1.744 to 0.934 given just 2500 rated items in our real-world dataset.
VILE is an ETS [Expert Tutoring System], it is a program that enables its users to learn/understa... more VILE is an ETS [Expert Tutoring System], it is a program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analyzing the user’s intelligence level. Our project takes into account a lot of tried-and-tested teaching mechanisms and aims at providing a platform that makes learning easier and more productive. We have tried to incorporate techniques such as Scaffolding, Socratic Questioning and Game based approaches in an Interactive Environment to facilitate learning of various courses. Each user’s data is maintained and analyzed to determine the ZPD of each user and customize teaching techniques as per each user’s intelligence. Our system records feedback and an automated sentiment analyzer is used to grade the feedback as positive or negative, which then is reported to the instructor for further course improvement. All of this cumulative data is analyzed and courses are graded and suggested to new users who wish to register.
An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a ... more An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analysing the user’s intelligence level. The paper explains a lot of tried-and-tested teaching mechanisms and aims at providing suggestions to engineer a platform that makes learning easier and more productive.
An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a c... more An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analysing the user’s intelligence level. The paper explains a lot of tried-and-tested teaching mechanisms and aims at providing suggestions to engineer a platform that makes learning easier and more productive.
The exponential increase in the use of the Internet and social media over the last two decades ha... more The exponential increase in the use of the Internet and social media over the last two decades has changed human interaction. This has led to many positive outcomes, but at the same time it has brought risks and harms. While the volume of harmful content online, such as hate speech, is not manageable by humans, interest in the academic community to investigate automated means for hate speech detection has increased. In this study, we analyse six publicly available datasets by combining them into a single homogeneous dataset and classify them into three classes, abusive, hateful or neither. We create a baseline model and we improve model performance scores using various optimisation techniques. After attaining a competitive performance score, we create a tool which identifies and scores a page with effective metric in near-real time and uses the same as feedback to re-train our model. We prove the competitive performance of our multilingual model on two langauges, English and Hindi, leading to comparable or superior performance to most monolingual models.
This paper explores the use of content-based and SVD filtering algorithm to increase the efficien... more This paper explores the use of content-based and SVD filtering algorithm to increase the efficiency and accuracy for a small subset of data-set. For mid-sized companies where data is scarce the existing algorithms for a recommendation system are futile. But Recommender systems have proven to be a valuable tool for web companies like Amazon and Netflix for attracting and maintaining a large user base as they have large dataset. Here in this paper we are using Yelp.com 1 data from a single city. We present the method to combine two approaches, and find that the MSE for predicting a user's new rating can be reduced from a baseline MSE of 1.744 to 0.934 given just 2500 rated items in our real-world dataset.
VILE is an ETS [Expert Tutoring System], it is a program that enables its users to learn/understa... more VILE is an ETS [Expert Tutoring System], it is a program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analyzing the user’s intelligence level. Our project takes into account a lot of tried-and-tested teaching mechanisms and aims at providing a platform that makes learning easier and more productive. We have tried to incorporate techniques such as Scaffolding, Socratic Questioning and Game based approaches in an Interactive Environment to facilitate learning of various courses. Each user’s data is maintained and analyzed to determine the ZPD of each user and customize teaching techniques as per each user’s intelligence. Our system records feedback and an automated sentiment analyzer is used to grade the feedback as positive or negative, which then is reported to the instructor for further course improvement. All of this cumulative data is analyzed and courses are graded and suggested to new users who wish to register.
An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a ... more An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analysing the user’s intelligence level. The paper explains a lot of tried-and-tested teaching mechanisms and aims at providing suggestions to engineer a platform that makes learning easier and more productive.
An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a c... more An ETS or an Expert Tutoring System is any program that enables its users to learn/understand a concept or topic and is able to customize its strategies by analysing the user’s intelligence level. The paper explains a lot of tried-and-tested teaching mechanisms and aims at providing suggestions to engineer a platform that makes learning easier and more productive.
Uploads
Papers by Shanky R Sharma