Home | About Me | Teaching & Academics | Research Interest | Presentations | Publications | What Else I Enjoy | Blog
smile-please

Research Interests

For projects that me and my team are currently working on please CLICK HERE

I work in the broad areas of Web Science and Data Analytics. In specific, my interests include Social Network Analysis, Bias & Privacy in the Web and Action Recognition in Sports Videos. I worked in Formal Language and Automata Theory for a considerable amount of time previously.

Social Network Analysis
Social synchrony is a phenomena studied in social science. We study this phenomena is social media networks and define it in a formal way. We define a method to detect this phenomena is the Twitter network and define additional methods to predict if this phenomena is about a specific event or not. One of the measures that we define is herding behavior. This study leads us to look into the unique behavioral pattern of users espeically in Twitter network. In addition to this we also examine how this behavior is mapped to different kind of events - periodical events, aperiodical events, one-off events and so on.

Bias and Privacy
Web is pervasive these days. User data is present all over the web in various formats. These days the data in various formats can be collated from the public domain in an automated way, integrated and augmented to get to know more about the users personal information. Hence it has become imminent that people who are using the web and people who are managing the web (in social media both are almost the same!) to take care of the privacy and the security part of the user data in the web. In addition to this human's inherent bias are present all over the internet in the data and these days with ML algorithms applied on it, even the ML algorithms gets learned to get biased in a huge way. This affects people who use the ML algorithms to make decision. Moroever in the name of personalisation people get data related to their preference and there comes the effect of filter bubble. So our work on these two problem attempts to study the bias present in Google Ad personalisation, Google search, bias in media and various provacy issues present in Indian government websites.

Action Recognition in Sports Videos
In general, vidoes are unstructured data. So searching in videos is a highly non-trivial task. In our work we take sports videos and using various patterns in the video we attempt to label it in an automated fashion, by using various techniques so that it becomes searchable or segmentable. For this, we take the cricket videos as the source and attempt to do the labeing especially those parts which consists of deliveries (by a deliver we mean the segment of video where a ball being bowled and a batsman hitting and scoring some runs). First we take a delivery as our focus of interest in the circket videos and build a benchmark dataset that consists of only deliveries. This creation of dataset is itself a challenging task. But once it is done it becomes a benchmark for addressing various other problems. For example, this dataset becomes our training data for our work on classifying the cricket shots. Once we are able to classify the cricket shots we will be able to automatically label the cricket videos with respect to various cricket shots played. This makes the cricket videos searchable and segmentable with respect to various cricket shots played. More details can be found from my student Arpan's page.

Indian Classical Music Information Retrieval and Analysis
This is the work I have started to explore very recently. Here we are working on a problem called thumbnailing in Indian classical music. For example from an audio segment of Indian classical music we want to find the pattern or the phrase that repeats often. We feel that this can be one of the represetnation for that song in consideration. This work I am presently doing with a team in IIITH headed by Dr. Suryakanth.

Students Guided/Guiding

Doctor of Philosophy (Ph.D)
  1. Nirmal Kumar Sivaraman - Social Synchrony Detection and Study of Herding Behavior and Events in Social Media (ongoing)
  2. Arpan Gupta - Action Recognition in Cricket Videos (ongoing)
Post Graduates (M.Tech)
  1. Deepti Sharma - Agenda-Setting Effect of Media and Party Handles in Shaping the Public Opinion in Indian General Election 2014 and 2019 on Twitter Platform - graduated in July 2019 - Presently a PhD student in MNIT, Jaipur
  2. Shaily Goyal - Exploratory Data Analysis of Burst Patterns in activities of Twitter Users - graduated in July 2019
  3. Sourabh Mathur - Twitter User Profiling and Classification - Graduated in July 2017 - working in Zeotap
  4. Mansi Atolia - Opinion Churning in Online Social Media - Graduated in July 2017 - working in QDegree Services, Jaipur
Under Graduates (B.Tech)
(Selected ongoing ones)
  1. Nisha Shekhawat and Aakanksha Chauhan - Bias in Google Ad Settings and Google Search
  2. Aditya Bhattacharjee - Thumbnailing in Indian Classical Music
  3. Vibhor Agarwal and Yash Vekaria - Measuring Herding Behavior in a Social Synchrony
Copyright © 2017 M Sakthi Balan.
email