I am Lokesh Todwal a final year undergraduate student at the Department of Computer Science and Engineering (CSE) at LNMIIT, Jaipur. During the daytime you would find me glued to my laptop, at night I fight ninjas. I love to explore new technologies and always looking forward for challenging problems.

I’ve been a proactive researcher and a result driven technology enthusiast with interest in Data Analytics and Web Science. Currently, I am working with Dr. Sakthi Balan M. (Assoc. Prof) and Mr. Nirmal Kumar Sivaraman (Asst. Prof) on "Qualitative Analysis of Social Synchrony in Twitter". In this work, we are trying to analyse collectives or groups of users in terms of two cognitive dimensions called Abstraction and Expression
I am also co-author of topic Sentiment and Emotion Analysis of Tweets Regarding Demonetization” written on the blog.

Complete CV


IIIT, Banglore

June, 2017 - July, 2017

Summer Research Internship

Worked on the research project called ”Modeling Online Social Cognition as a Marketplace of Opinions” with Prof. Srinath Srinivasa and created a Web App called Mithya for identifying opinion drivers and directions on social media.

Nov, 2016 - Present


Mentorring the students for the course: Machine Learning by Stanford University. Awarded with ”Coursera Mentor-3 Month” badge by Coursera as a token of appreciation

IIT, Bhubaneswar

May 2016 - June 2016

Summer Research Internship

Developed an Android application that calculates pulse rate along with quality of ECG and PPG Signals received from the patient, by performing certain number of operations.


Dec, 2015 - Jan, 2016

Winter Research Internship

Developed data Visualization dashboards using D3.js. One is on Armed Forces These dashboards are created using HTML, CSS and JavaScript.


LNMIIT, Jaipur

July, 2014 - Present

Bachelors of Technology(Pursuing)

Branch:  Computer Science Engineering(CSE)

CGPA: 7.72/10

Army Public School, Jaipur

April, 2012 - May, 2013

Senior Secondary Education

Percentage: 88.2%

Army Public School, Jaipur

April, 2010 - March, 2011

Secondary Education

CGPA: 9.4/10


  • Nirmal Kumar S, Sakthi Balan M, Pushkal Agarwal and Lokesh Todwal. On Social Synchrony in Online Social Networks . Poster accepted at ACM Web Science Conference, Troy, New York, USA, July 2017 (WebSci’17).
  • Pushkal Agarwal, Lokesh Todwal, Nirmal Kumar S and Sakthi Balan M. "Sentiment And Emotion Analysis Of Tweets Regarding Demonetisation". CSI Communication. 2017 April; Volume 41(Issue 1): Page 21-23.


Libraries/Packages Used















Data Visualization Tool




Click on logo to view certificate

October 1, 2016

Coursera Mentor Community and Training Course

September 4, 2016

Reproducible Research by Johns Hopkins University

August 31, 2016

Exploratory Data Analysis by Johns Hopkins University

August 27, 2016

Machine Learning Foundations: A Case Study Approach by University of Washington

August 21, 2016

Machine Learning by Stanford University

August 5, 2016

Fundamentals of Visualization with Tableau by University of California, Davis

July 6, 2016

Getting and Cleaning Data by Johns Hopkins University

June 9, 2016

R Programming by Johns Hopkins University

March 27, 2016

Data Structures and Performance by University of California, San Diego

March 6, 2016

The Data Scientist’s Toolbox by Johns Hopkins University

February 4, 2016

Introduction to Big Data (2015) by University of California, San Diego

February 2, 2016

Object Oriented Programming in Java by University of California, San Diego


Grading System

Developed using Shiny package of R, in which a faculty can upload the csv or tsv file containing marks of the students and can select what kind of grading faculty wants to have (relative or absolute) based on which a graph is plotted along with other informations and finally faculty can download the csv file having the grade of each user.

Technology used was: R(Package: Shiny(html of R))


Visualized the clusters of Twitter Followers on World Map. Used the twitter API to fetch the data of tweeters on particular topic inserted by the user in the input box and NbClust to get the optimum clusters to be visualized and then used kmeans clustering on them to get the optimum clusters. It will tell us the places where the users are active or are concerned about the topic.

Technology used was: R(Package: Shiny(html of R), twitteR, NbClust, ggmap, map, ggplot2)

Sentiment Analysis of Tweets

Used Twitter API to extract the tweets with the help of TwitteR package and then used sentiment package in R to classify the emotions and polarity. Also used wordcloud library to visualize the sentiment.

Technology used was: R(Pacakge: TwitteR, Sentiment)

Analyzing product sentiment

Trained a sentiment analysis model using a set of key polarizing words, verify the weights learned to each of these words, and compare the results of this simpler classifier with those of the one using all of the words.

Technology used was: Python(Libraries: pandas, numpy, Graphlab, scikit)

Song Recommendation

Build recommender system to find products, music and movies that interest users and compared the simple popularity-based recommendation with a personalized model, and showed the significant improvement provided by personalization using model based collaborative filtering.

Technology used was: Python(Libraries: pandas, numpy, Graphlab, scikit)

Retrieving Wikipedia articles

In this I focused on using nearest neighbors and clustering to retrieve documents that interest users, by analyzing their text. I also explored two document representations: word counts and TF-IDF

Technology used was: Python(Libraries: pandas, numpy, Graphlab, scikit)

Online Shopping Portal

Developed a shopping portal in which user can search the item available in the database, can view, add the products to cart(or wish list) and can buy further, while the admin can add the products to the database.

Technology used were: Java, JSP, Servlet, MySQL, JQuery.

Smart Text Editor

Built a smart text editor/processor that incorporates “intelligent” behaviors of modern-day text interfaces including autocomplete, flagging misspelled words and spelling auto-correct.

Technology used: Java

CPU Simulator

This is a program in C where it fetch assembly code from file and convert it into binary code, which is sent to another file and then the binary file as an input finds the answer.

Data Visualization using Web Technologies

Case Study

Data Cleansing and acquisition

The project successfully attempted fetching and management of data collected from the accelerometers from the Samsung Galaxy S smartphone, tidying the data set for subsequent analysis. The final R script consisted of appropriately labeled data set with descriptive variable names, and an independent tidy data created from this cleansed data set, with the average of each variable for each activity and each subject.

Fine Particulate Matter Air Pollution

The project successfully attempted fetching and management of data collected from UC Irvine. The study is related to Particulate matter (less than 2.5 microns in diameter) from two years, 1999 (when monitoring of particulate matter started) to 2012. The final R script consisted of appropriately labeled data set with descriptive variable names and noticed decline in this type of air pollution between these two years.



BH1, A126, LNMIIT Jaipur, India

Mobile no.

(+91) 9462999051