Avatar

Sagar Joglekar, Ph.D.

Machine Learning Scientist

Expedia Group

Biography

I am a Machine Learning Scientist at the Expedia Group, working with the content data science team. We work on development of platforms and models that handle curation, ranking, and recommendation of user generated content (text, images, tags, ratings, etc).

Previously, I was a Reserch Scientist at Nokia Bell labs, Cambridge UK, working with the social dynamics team, where I did blue sky research around ideas to quantify human processes from large scale data.

I am mainly interested in research problems that pertain to building strong representations of human behaviour from data, using methods from complex networks, machine learning, and computer vision.

I was a King's India scholar at King's College London, where I worked on my Ph.D. in computer science at the Department of Informatics, under the guidance of Dr. Nishanth Sastry.

I have graduated with a Masters of Science (M.S.) degree from University of California at Santa Barbara USA, majoring in signals processing and networks, and a Bachelors of Engineering (B.Eng) from University of Pune India, majoring in Electronics engineering .

Interests

  • Complex Networks
  • Computer Vision
  • Computational Social Dynamics
  • Representation learning

Education

  • Ph.D. in Computer Science, 2015 - 2019

    King's College, London, U.K.

  • Master of Sciences (M.S) , Major in Signals Processing and Networks, 2010 - 2012

    University of California, Santa Barbara, C.A. , U.S.A

  • B.Eng , Electronics Engineering, 2004 - 2008

    University of Pune, India

Posts

Sensing the real world through NHS prescriptions data

Researchers and practitioners intererested in geography of health, social dynamics, economics, and everything in between are always …

The cost of being on the fence.

After 2.5 years of association with Nokia Bell Labs, I have decided to move on to do something else. I will be moving into a more …

Broad areas of work

Quantifying the Urban Exposome

The 21st century would witness one of the largest urban migration in human history. A lot of research has gone into understanding the effects of the urban life on physical and mental health. The results have been unanimous: The urban environment has long lasting impacts on our well being. The facets of our urban environment that impact on our health and well being are called the urban exposome. In these projects, I attempt to quantify this exposome using techiques from deep learning, complex network, GIS, and NLP.

Social networks and health

We as a soceity have accepted the internet as an extension of the self. The online disinhibition effect sometimes allows us to open up to strangers in order to seek support, or disclose proxies for medical conditions in the process of being social on the networking platforms. In these works, I explored different models in order to capture these concepts, using methods from complex networks and NLP.

Measuring the partisan web and its effects

The internet has made seamless access to information channels, a reality. As a result, a lot of issues of the offline world, are now being voiced, shared, and discussed on the internet; including but not limited to partisan and hot button issues. As a result, phenomenona like fake news and polarising partisan news have become a central theme for inter-disciplinary research. These works investigate the hyper-partisan ecosystem and other social media processes that may have profound effects on how democracy functions in our post internet world

Quantifying engagement in networked systems

There has been a churn of new platforms exploring new ways to network people, and their content. From primacy driven social media platforms like Tik-tok, Vine and Instagram, to a more decentralized socially curated content platform like Mastodom. These works explore models, methods, and pipelines to measure how humans adopt and interact with these new and innovative platforms.

Experience

 
 
 
 
 

Machine Learning Scientist

Expedia Group

Jul 2021 – Present London, UK
I work with the Content Data Science team to develop machine learning algorithms and services that deal with curation, ranking, and retrieval of any and all content hosted on the Expedia Group products.
 
 
 
 
 

Research Scientist

Nokia Bell Labs

Jun 2019 – Jul 2021 Cambridge, UK
As a member of the Bell labs social dynamics team, I have been working on questions that try to redefine our relationships with data. I primarily work on problems dealing with machine learning and statistical inference with a stress on impacts on healthcare and urbanism. The work generally involves mathematically modelling an off-line phenomenon through the online data that it generates.
 
 
 
 
 

Head of Research

Firedrop.ai

Apr 2016 – Jun 2017 London, UK
Research and Development. Advisor for all things ML
 
 
 
 
 

Senior Software engineer

Citrix systems

Feb 2012 – Sep 2015 Santa Barbara, California, USA
Development of distributed media encoder/decoder protocols for the client/server side libraries used in Citrix collaborations and conferencing products (e,g, GoToMeeting , GoToAssist, GoToWebinar)
 
 
 
 
 

Research Engineer

Infosys research Labs

Jul 2008 – Jul 2010 Bangalore/Pune India
Research, prototyping, and development hand over in state of the art DRM, multimedia security and delivery systems

Selected Publications

Quickly discover relevant content by filtering publications.

How epidemic psychology works on Twitter: evolution of responses to the COVID-19 pandemic in the US

Disruptions resulting from an epidemic might often appear to amount to chaos but, in reality, can be understood in a systematic way …

The Healthy States of America: Creating a Health Taxonomy with Social Media

Since the uptake of social media, researchers have mined online discussions to track the outbreak and evolution of specific diseases or …

Jane Jacobs in the Sky: Predicting Urban Vitality with Open Satellite Data

The presence of people in an urban area throughout the day – often called ‘urban vitality’ – is one of the …

KAIROS: Talking Heads and Moving Bodies for Successful Meetings

Successful meetings create a safe environment for contribution; one that attendees feel engaged in and part of. Previous research has …

Ranking comment sorting policies in online debates

Online debates typically possess a large number of argumentative comments. Most readers who would like to see which comments are …

Recent & Upcoming Talks

Ph.D. Defence talk
CTR_workshop
SocInfo2017