Md Main Uddin Rony

3413 Tulane Dr, Apt 02, Hyattsville, MD 20783 · (662) 380-9260 · mrony@umd.edu

I am a Ph.D. student at the College of Information Studies (iSchool) of the University of Maryland, College Park. My research interests include Data Mining, Machine Learning, NLP, Social Network Analysis, and Computational Journalism. To be more specific, I am much interested in developing computational solutions to ensure the quality of information surfacing on social media. Currently, I am working as a Research Assistant for my academic supervisor, Dr. Naeemul Hassan, who also leads the Computational Journalism Lab at the University of Maryland. I completed my MS in Engineering Science (Emphasis Computer Science) from the University of Mississippi (Ole Miss) and a BSc in Computer Science and Engineering from the Bangladesh University of Engineering and Technology (BUET).


Recent News

Mar 1, 2021 Alhamdulillah! I will be joining Adobe this summer as an HCI research intern.
Dec 23, 2020 Alhamdulillah! Our paper titled "Exploring the Tensions between the Owners and the Drivers of Uber Cars in Urban Bangladesh" has been accepted in CSCW 2021.
Dec 12, 2020 Alhamdulillah! Our paper titled "Does Clickbait Actually Attract More Clicks? Three Clickbait studies you must read" has been accepted in CHI 2021.
Aug 31, 2020 Alhamdulillah! Our short paper titled "ClaimViz: Visual Analytics for Identifying and Verifying Factual Claims" has been accepted in the 2020 IEEE VIS.
May 19, 2020 Alhamdulillah! Our paper titled "Varying amounts of information in health news headlines can affect user selection and interactivity" has been accepted in AEJMC 2020.
Sep 10, 2019 Alhamdulillah! Our paper titled Examining the Role of Clickbait Headlines to Engage Readers with Reliable Health-related Information" has been accepted for presentation at the AAAI 2019 Fall Symposium on AI for Social Good.
Aug 8, 2019 Alhamdulillah! Joined University of Maryland, College Park as a Graduate Teaching Assistant
Jul 30, 2019 Left University of Mississippi
Jul 11, 2019 Alhamdulillah! I have successfully defended my MS Thesis titled "Towards Misleading Connection Mining"
Jul 05, 2019 Alhamdulillah! Our manuscript titled "Misleading Connection Mining: Scopes, Computational Challenges and Future Directions" has been accepted as a poster in SocInfo 2019
May 14, 2019 Attended MisinfoWorkshop 2019 at San Francisco and presented our work titled "Differences in Health News from Reliable and Unreliable Media"
Feb 25, 2019 Alhamdulillah! Our paper titled "Differences in Health News from Reliable and Unreliable Media" has been accepted in the MisinfoWorkshop 2019
Feb 1-2, 2019 Presented our works at C+J Symposium, 2019, Miami, FL, US
Nov 29, 2018 Alhamdulillah! Paper titled “A Large-scale Study of Social Media Sources in News Articles” has been accepted in C+J 2019
Nov 29, 2018 Alhamdulillah! Paper titled “Fact-checking Initiatives in Bangladesh, India, and Nepal: A Study of User Engagement and Challenges” has been accepted in C+J 2019
Oct 31, 2018 Paper titled “Fact-checking Initiatives in Bangladesh, India, and Nepal: A Study of User Engagement and Challenges” submitted in C+J 2019
Oct 31, 2018 Paper titled “Differences between Health Related News Articles from Reliable and Unreliable Media” submitted in C+J 2019
Oct 31, 2018 Paper titled “A Large-scale Study of Social Media Sources in News Articles” submitted in C+J 2019
May 15, 2018 Alhamdulillah! Paper titled “All the President’s tweets”: A Large-scale Study of Uses of Social Media Content in Online News” has been accepted in AEJMC 2018
Jan 17, 2018 Alhamdulillah! Our paper titled “Boon or Bane for Political Engagement: A Large-Scale Study of Normalization of Facebook” has been accepted in the 68th annual ICA conference, to be held in Prague, Czech Republic.
Jan 17, 2018 Alhamdulillah! Our paper titled “Social Media as Source: A Large-scale Study of Mainstream and Unreliable News Sites” has been accepted in the AEJMC Midwinter Conference, 2018
Nov 09, 2017 Alhamdulillah! Our paper titled “BaitBuster: A Clickbait Identification Framework” submitted to AAAI 2018 demonstration track has been accepted
Nov 01, 2017 Paper titled “Boon or Bane for Political Engagement: A Large-Scale Study of Normalization of Facebook” submitted to ICA 2018
Sep 29, 2017 Paper titled “BaitBuster: A Clickbait Identification Framework” has been submitted to AAAI 2018 Demonstration track
Sep 04, 2017 Alhamdulillah! Our paper titled “BaitBuster: Destined to Save You Some Clicks” has been accepted in the 2017 Computation+Journalism symposium as a demo/poster.
Aug 1, 2017 Paper titled “BaitBuster: Destined to Save You Some Clicks” submitted to Computation+Journalism symposium 2017.
Jun 1, 2017 Paper titled “A Boon, Bane, or None for Political Engagement: Normalization of Facebook in 2016 U.S. Presidential Election Campaign” submitted to JMCQ 2017.
May 24, 2017 Paper titled “NMAT: Interactive Tool for Analyzing News Media on Social Platforms” submitted in CIKM 2017.
May 15, 2017 Alhamdulillah! Our paper titled “Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects?” has been accepted in ASONAM 2017 as a full paper.
Mar 26, 2017 Paper titled “Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects?” submitted in ASONAM 2017.

Research Projects

Clickbait Practice on Social Media

The term clickbait refers to a form of web content that employs writing formulas and linguistic techniques in headlines to trick readers into clicking links, but does not deliver on its promises. Although media scholars and pundits consistently show clickbait content in a bad light, the industry based on this type of content has been rapidly growing and reaching more and more people across the world. The growth of clickbait industry appears to have noticeable impact on the media ecosystem, as many traditional media organizations have started to use clickbait techniques to attract readers and generate revenue. The key purpose of this project is to systematically quantify the extents to which traditional print and broadcast media as well as the “unreliable” media use clickbait properties in contents published on the web.

Read Paper Presentation Poster
BaitBuster: Clickbait Solution Framework

BaitBuster is a clickbait solution framework which aims to improve the web surfing experience of general users. It consists of a browser extension that identifies clickbaits present in a Facebook timeline and a Facebook page which is administered by a bot through the Facebook API. It not only detects clickbaits floating on the web but also provides a brief explanation behind its action. The extension is publicly available for use.

Read Paper Presentation Poster Website Chrome Extension
Fact Checking in South Asian Countries

Fake news and misinformation spread in developing countries as fast as they do in developed countries with increasing penetration of the internet and social media. However, fighting misinformation is more difficult in developing countries where resources and necessary technologies are scarce. The main purpose of this project is to identify the challenges various fact-checking initiatives face in three South Asian countries–Bangladesh, India, and Nepal and recommend a sustainable solution.

Read Paper Presentation
Combating Health Disinformation

Misinformation spreading is an issue that attracts the attention of many researchers. But health disinformation is a relatively unexplored area. Consequences of misleading or erroneous health news can be very critical. Believing health misinformation may lead to a hazardous health condition. The goal of this study is to identify the structural, topical, and semantic patterns which are different in contents from reliable and unreliable media outlets. We believe these patterns can be leveraged to build a machine learning based solution for combating the health disinformation problem.

Read Paper Presentation Poster
Social Networking Sites as a News Source

Media organizations use Social Networking Sites (SNSs) not only as a medium of news dissemination but also as a source of news collection. Journalists like to quote and paraphrase contents regularly from social media pages. This project aims to investigate social media sourcing pattern from different perspectives.

Read Paper Poster
Political Engagement over Social Media

This project investigated the influence of social media in the election campaign based on a theoretical framework named "Normalization of the Cyberspace". We examined engagement on two verified Facebook pages run by the campaigns of two main candidates of the 2016 U.S. presidential election—Donald Trump and Hillary Clinton. We combine two computational methods—sentiment analysis and automated topic classification—and a quantitative content analysis method to analyze user engagement data.

Read Paper Poster
ClaimViz: Visual Analytics for Fact-checking

Determining the veracity of a factual claim made by public figures, aka fact-checking, is a common task of the journalists in the newsrooms. One critical challenge that they face while fact-checking is- they have to swift through a large amount of text to find claims that are checkworthy. While there exist some computational methods for automating the fact-checking process, little research has been done on how a system should combine such techniques with visualizations to assist journalists. ClaimViz is a visual analytic system that integrates machine learning methods with interactive visualizations to facilitate the fact-checking process for journalists. The design of ClaimViz is based on analyzing the requirements of real fact-checkers and our case studies demonstrate how the system can help users to effectively spot and verify claims.

  • Md Main Uddin Rony, Enamul Hoque, Naeemul Hassan.ClaimViz: Visual Analytics for Identifying andVerifying Factual Claims.In Proceedings of the IEEE Information Visualization Conference, October, 2020. [Paper] [Presentation] [Demo]
Designing Effective Health News

Mass media plays a central role in delivering science-based crisis, risk, and healthcare information to the general public. However, we have shown a gap between what scholars and expert practitioners advise based on scientific guidelines and what mass media communicates about risk and healthcare. This project test AI, NLP, and data visualization methods to see how well they can close the gap between best practices in communicating science-based knowledge and current mass media practices focusing primarily on news stories. Our approach can assist mass media content creators in preparing effective and high-quality health information that conforms to science-based criteria, and assist media consumers in finding the highest quality information.


Publications

Md Main Uddin Rony, Enamul Hoque, Naeemul Hassan.ClaimViz: Visual Analytics for Identifying andVerifying Factual Claims. In Proceedings of the IEEE Information Visualization Conference, October, 2020. [Paper] [Presentation] [Demo]
Ron Yaros, Md Mahfuzul Haque, Md Main Uddin Rony, Naeemul Hassan.Varying amounts of information inhealth news headlines can affect user selection and interactivity. In Proceedings of the Association for Educationin Journalism and Mass Communication (AEJMC) conference, San Francisco, USA, August, 2020 [Paper] [Poster]
Sameer Dhoju, Md Main Uddin Rony, Muhammad Ashad Kabir, Naeemul Hassan. Differences in Health News from Reliable and Unreliable Media. In Companion Proceedings of The 2019 World Wide Web Conference, pp. 981-987. ACM, 2019. [Paper] [Poster]
Md Mahfuzul Haque, Mohammad Yousuf, Zahedur Arman, Md Main Uddin Rony, Ahmed Shatil Alam, Kazi Mehedi Hasan, Md Khadimul Islam, Naeemul Hassan. Fact-checking Initiatives in Bangladesh, India, and Nepal: A Study of User Engagement and Challenges. In Proceedings of the 2019 Computation+Journalism Symposium (C+J2019), Miami, USA, February, 2019. [Paper]
Md Main Uddin Rony, Mohammad Yousuf, Naeemul Hassan. A Large-scale Study of Social Media Sources in News Articles. In Proceedings of the 2019 Computation+Journalism Symposium (C+J2019), Miami, USA, February, 2019. [Paper] [Poster]
Mohammad Yousuf, Naeemul Hassan, Md Main Uddin Rony. Social Media as Source: A Large-scale Study of Mainstream and Unreliable News Sites. In Proceedings of the Association for Education in Journalism and Mass Communication (AEJMC) Midwinter conference, Oklahoma, USA, March, 2018.
Mohammad Yousuf, Naeemul Hassan, Md Main Uddin Rony. Boon or Bane for Political Engagement: A Large-Scale Study of Normalization of Facebook. In Proceedings of the 68th International Communication Association (ICA) annual conference, Prague, Czech Republic, May, 2018. [Paper]
Md Main Uddin Rony, Naeemul Hassan, Mohammad Yousuf. BaitBuster: A Clickbait Identification Framework. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), New orleans, Louisiana, USA, February, 2018. [Paper] [Poster]
Md Main Uddin Rony, Naeemul Hassan, Mohammad Yousuf. BaitBuster: Destined to Save You Some Clicks. In Proceedings of the 2017 Computation+Journalism Symposium (C+J2017), Illinois, October, 2017. [Paper]
Md Main Uddin Rony, Naeemul Hassan, Mohammad Yousuf. Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects?. In Proceedings of 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2017), July, 2017. [Paper] [Poster]

Experience

Research Assistant

The University of Maryland

Currently, I am a Research Assistant at Computational Journalism Lab (CJLab). CJLab is a research facility in the Philip Merrill College of Journalism at the University of Maryland, College Park. The goal of this lab is to advance the field of computational journalism by exploring interdisciplinary problems at the intersection of computation, information science, and journalism and thereby address issues with big societal impact.

  • Carrying out a comprehensive review of misleading news articles, including its characterization, existing algorithms from a data mining perspective, and representative datasets.
  • Studying the impact of news headlines of health-related news articles on creating audience engagement.
  • Developing an interactive visualization tool to help the fact-checkers in identifying and verifying check-worthy factual statements from a large transcript.
Technologies:

Python Flask Deep Learning Machine Learning RNN CNN KERAS SCIKIT-LEARN Google Cloud

January 2020 - Present

Teaching Assistant

The University of Maryland, College Park

Currently, I am working as a Teaching Assistant for Dr. Amanda Lazar and Ed Summers.

  • INST 126 (Fall 2019)
August 2019 - December 2019

Research Assistant

The University of Mississippi

I worked as a Research Assistant for Dr. Naeemul Hassan, a computer science professor at the University of Mississippi, on several projects since January 2017. Dr. Hassan directs Data Exploration and Research Laboratory (dear.lab). The goal of this lab is to advance database and data mining research and thereby address issues with big societal impact. The lab's current focus includes computational journalism, multidimensional optimization, and natural language processing.

  • Collecting, processing, cleaning and verifying the integrity of data used for analysis
  • Selecting features, building and optimizing classifiers using machine learning techniques
  • Trying to build new deep learning based models for text processing
  • Applying the developed machine learning algorithms to solve real life problems
Technologies:

Python Flask Deep Learning Machine Learning RNN CNN KERAS SCIKIT-LEARN Google Cloud

January 2017 - July 2019

Software Engineer

Infolytx Inc.

My quest for Data Analytics began when I joined Infolytx as a Software Engineer. I was very lucky as I got the opportunity to learn from Dr. Zunaid Kazi, a former IBM researcher, directly. Infolytx is an AI and Machine Learning company building solutions to help healthcare and other high-tech industries understand and monetize their data.

  • Collecting, cleansing, collating data from 3rd parties and various open sources to prepare for analyzing
  • Carrying out analysis of the given data, drawing conclusion and developing recommendations, inferences, time series analysis using different Machine learning algorithms and statistical techniques
  • Manipulating data for data visualization and graphical report generation
Technologies:

Python Flask JAVA Machine Learning Ruby on Rails Rapid Miner SCIKIT-LEARN REST API

PharmacoWatch

A Java-based PaaS Solution where content from sources like FDA and social media has been parsed, analyzed using Big Data technology to build a Machine Learning Predictive Model for adverse drugs reaction intelligence.

Key Technologies Used:

Hadoop RapidMiner-ML package cTakes - Clinical Text Analysis platform NLP

Learn More Demo
Pharmalytx

A data-driven physician ranking and drug sales recommendation device built on analysis of large amount of 3rd party physician biographical data and prescription data.

Key Technologies Used:

Java RapidMiner-ML package Xamarin(Cross-platform for both iOS and Android)

Learn More Demo
RetailAR

An Augmented Reality App for customers where the retailer is able to advertise specials using 3D imagery.

Key Technologies Used:

Ruby On Rails(Back End) Android(Front End)

Learn More Demo
June 2015 - December 2016

Junior Software Engineer

Nascenia IT

Right after the completion of undergrad study, I joined Nascenia IT. Nascenia developed web and mobile-based application for its North American and European clients.

  • Consuming different third party provided APIs and payment gateway for providing business solutions
  • Responsible for full lifecycle development of a system, from initial requirement gathering to design, coding, testing, documentation & implementation
  • Developing RESTFUL API services
Technologies:

Ruby Ruby on Rails HTML CSS JavaScript REST API XML SOAP

BrokerPro

It is a comprehensive Transportation Management Software (TMS) solution designed to make life easier for medium to large transportation intermediaries dealing in TL and LTL freight.

Key Technologies Used:

Ruby on Rails HTML CSS JavaScript MySQL

Visit Website
WELLTRAVEL

Welltravel is a platform which enables travelers to find and book flights, hotels and rental cars for their trip..

Key Technologies Used:

Ruby on Rails HTML CSS Bootstrap PostgreSQL SOAP REST

July 2014 - June 2015

Education

University of Maryland, College Park

PhD Candidate
Information Studies

Data Visualization, Introduction to Data Science, Computational Linguistics-II, Introduction to Human Computer Interaction
August 2019

University of Mississippi, MS, USA

Master of Science
Engineering Science (Emphasis Computer Science)
Thesis: Towards Misleading Connection Mining

Machine Learning, Natural Language Processing, Data Mining, Artificial Intelligence, Parallel Computing, Computer Architecture, Computational Journalism, Analysis of Algorithms, Randomized Algorithms, Research Method
January 2017 - July 2019

Bangladesh University of Engineering and Technology, Dhaka, Bangladesh

Bachelor of Science
Computer Science and Engineering
Thesis: Study on ATM/POS Switching Software for Banks

Algorithm Engineering, Artificial Intelligence, Assembly Language Programming, Compiler, Computational Geometry, Computer Architecture, Computer Graphics, Computer Networks, Data Communication, Data Structures, Database, Digital Electronics and Pulse Techniques, Digital Logic Design, Digital System Design, Discrete Mathematics, Image Porcessing, Mathematical Analysis for Computer Science, Object Oriented Programming Language(C++, Java), Microprocessors and Microcontrollers, Operating System, Software Development, Structured Programming Language(C)
March 2009 - June 2014

Skills

  • Programming Languages: C, C++, Java, Python, R, Ruby, Assembly Language(Intel 8086), LATEX
  • Web Programming: Ruby on Rails, Flask, HTML, CSS, JavaScript, jQuery, XML, SOAP, REST, JSON
  • Data Technology: Scikit-learn, Keras, Google Cloud Natural Language
  • DBMS: MySQL, Oracle, PostgreSQL, MongoDB(NoSQL)
  • Version Control System: Git

Services

  • Webmaster: Muslim Student Association at Olemiss
  • Reviewer: CSCW 2020, NSysS 2020, The Web Conference 2019, CIKM 2018, The Web Conference 2018, JDIQ 2018
  • Member: Notre Dame College Science Club, Notre Dame College English Club

Achievements

Certifications

Awards
  • 1st Runner Up - Intra class Artificial Intelligence Game Development Competition - University of Mississippi 2018
  • Outstanding Adoption of New Technologies and the Establishment of Significant Capabilities in Data Analytics - Infolytx Inc. 2016
  • Outstanding Demonstration Of Infolytx's Motto of "Learn, Do, Teach" - Infolytx Inc. 2016
  • 1st Runner Up - National Hackathon Mobile App Competition - ICT Ministry of Bangladesh 2014
  • 2nd Runner up - Hardware Project Show - Bangladesh University of Engineering and Technology 2013
  • 2nd Runner up - Intra Department System Analysis Contest - Bangladesh University of Engineering and Technology 2012
  • Government Scholarship (Talentpool) - Dhaka Education Board, Bangladesh 2009
  • Primary Scholarship (General) - Dhaka Education Board, Bangladesh 2000

Curriculum Vitae