Arjit Sachdeva

This is 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… Show more

This is 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

A big data project aimed at comprehensive data mining/aggregation/scraping, sentimental analysis and visualization to improve business decisions and outcomes.

This version of the software is able to present various visualizations based on sentiments expressed in a review for a particular product category(like mobiles) as well as a compressed summary about the positive points and negative points pointed out as a whole.

-Uses a combination of NLP algorithms to extract features… Show more

A big data project aimed at comprehensive data mining/aggregation/scraping, sentimental analysis and visualization to improve business decisions and outcomes.

This version of the software is able to present various visualizations based on sentiments expressed in a review for a particular product category(like mobiles) as well as a compressed summary about the positive points and negative points pointed out as a whole.

-Uses a combination of NLP algorithms to extract features, slight improvements upon the noun-based approach.

-A custom scoring algorithm, assigning scores from -1 to 1 based on the polarity.

-Intuitive charts for various parameters like frequency of mentions, individual and aggregate sentiment scores etc. Show less

Developed and contributed to a Face Detection Software for Defence Research and Development Organization, Ministry of Defence, India.

-Image processing implemented in Java via OpenCV.

-Detects and counts faces from Still images and video files.

-Works on a LIVE webcam feed too by applying the algorithm to each frame.

-Useful in high-security zones to maintain the ratio of people entering and exiting border areas.

This was meant to allow groups of users to share a whiteboard on the Internet and scribble anything they feel like - primarily targeting educational purposes. At the time of its development, there was no efficient way of doing so, as Google Docs featured textual collaboration only.

The product was used live in one of the events held at our annual tech fest, attended by over 300+ participants.

-User login and registration

-Features like user profiles, image uploading, albums, friend requests, in-app messaging/inbox, rating and commenting on an image, filtering images by 'public' and 'private'.

-Lazy loading of images.

-Normalized database schema design and queries for User table, Friends table, Comments, Images etc.

-Application back-end in PHP and MySQL.