Selected Publications

. Facelift_dataViz. Mapping and Visualizing Deep-Learning Urban Beautification, 2018.

Project Source Document

. JMIR2018. Network analysis of the structure and dynamics of the Asthma UK and British Lung Foundation (BLF) online communities., 2018.

PDF Project Video Source Document

. WWW2018. Illuminating an ecosystem of partisan websites, 2018.

Preprint Dataset Project

. SocInfo17. Like at First Sight: Understanding User Engagement with the World of Microvideos, 2017.

Preprint Project Source Document

. Structure of Fora. Structure and dynamics of online patients’ communities: the case of Asthma UK and BLF online fora, 2017.

Project Source Document

. MTAP2012. Robust transcoding resistant watermarking for H.264 standard, 2014.

PDF Project Source Document

. SRII 2012. An Innovative System for Remote and Automated Testing of Mobile Phone Applications, 2012.

PDF Project Source Document


Modelling User engagment with micro-videos

The up and coming formats of micro videos and stories, have allowed a new form of expression for social media users. The format however competes with the other contemporary formats of simple images and videos. The aim was to understand what sets this new format apart, and predict engagement patters using computational methods.

Modelling notion of support in online health communities

We as a soceity have accepted the internet as a way to express the most intimate secrets about us. Sometimes the upside of this is the availibility of a wider audience who can help one another at times of mental or physical distress. In this project, I attempt to quantify behavioural and conversational motifs of the notion of support through the analysis of a wide range of data streams.

Explaining Urban beauty

Buildings and neighbourhoods speak. They speak of egalitarianism or elitism, beauty or ugliness, acceptance or arrogance. The aim of this project is to celebrate egalitarianism, beauty, and acceptance by beautifying the entire world, one Google Street view at a time. All of this is done by designing state-of-the-art technologies that make it possible to smarten a street view and read inside the Deep Learning ‘black box’. Please try the demo app out here.

Measuring Hyper partisan news ecosystem

The project looks at how hyper-partisan news sources in the U.S. interact with each other and with their consumers. We work with a professionally curated seed dataset from Buzzfeed and analyse it using click throughs and Alexa traffic refers to understand how these hyper-partisan news sources create an echo-chamber of themselves.

Miscellaneous projects

Some miscellanious projects on Digital convergence, DRM, steganography, Computervision and networks

Recent & Upcoming Talks

May 4, 2018 2:00 PM
Sep 13, 2017 9:45 AM