Sri Teja Allaparthi

About Me

Hey there, welcome!

I'm currently working on Swipe with an awesome team. I did my Masters with major in Computer Science at IIIT Hyderabad, worked with Assoc. Prof. Vikram Pudi with focus on Data Mining, Machine Learning and Information Retrieval. I also did my bachelor's degree in the Department of Computer Science at IIIT Hyderabad, India.

Research Interest

My work has been primarily focused on knowledge - both acquiring knowledge from text, and using structured knowledge to power downstream applications. Currently, I am working on Controversy Detection. Previously, I've worked on Medical Data Mining, Information Retrieval and Natural Language Processiing.

Publications

• Allaparthi, Sri Teja, Ganesh Yaparla, and Vikram Pudi. "Sentiment and Semantic Deep Hierarchical Attention Neural Network for Fine Grained News Classification." 2018 IEEE International Conference on Big Knowledge (ICBK). IEEE, 2018.

  Abstract

  The purpose of this study is to examine the differences between different types of news stories. Given the huge impact of social networks, online content plays an important role in forming or changing the opinions of people. Unlike traditional journalism where only certain news organizations can publish content, online journalism has given chance even for individuals to publish. This has its own advantages like individual empowerment but has given a chance to a lot of malicious entities to spread misinformation for their own benefit. As reported by many organizations in recent history, this even has influence on major events like the outcome of elections. Therefore, it is of great importance now, to have some sort of automated classification of news stories. In this work, we propose a deep hierarchical attention neural architecture combining sentiment and semantic embeddings for more accurate fine grained classification of news stories. Experimental results show that the sentiment embedding along with semantic information outperform several state-of-the art methods in this task.

• A. Sriteja, P. Pandey and V. Pudi, "Controversy Detection Using Reactions on Social Media," 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 2017, pp. 884-889.

  Abstract

  In this work we demonstrate a method to detect controversy on news issues. This is done by performing an analysis of people's reaction on social media to news articles reporting these issues. Detecting controversial news topics on web is a relevant problem today. It helps to identify the issues upon which people have divided opinion and is specially useful on topics such as a presidential election, government reforms, climate change etc. We use sentiment analysis and word matching to accomplish this task. We show the application of our method for detecting controversial topics during the US Presidential elections 2016.

Projects

Here are some of my projects:

• Machine Learning - Medical Data Analysis using Dynamic Decision Trees
  Implemented a model which automatically learns the hidden patterns in the medical data available from different blogs over the web and identifies the diseases and classify accordingly to facilitate the feature of learning the symptoms accurately and map them to the possible diseases.
• Machine Learning - Chemical Named Entity Recognition
  Obtaining previous knowledge on chemicals, such as biological properties or toxic effects, can help in many aspects of drug development processes. In this project we discussed various algorithms implemented to extract chemical information and chemical-related entities such as drug names and source materials from text in several domains such as bioinformatics and nanoinformatics. We compared the performances of these algorithms with each other.
• Information Retrieval - Wikipedia Search engine
  Fetching pages from Wikipedia dump by analyzing the multiple query words, the size of index was less than quarter of the size of Wikipedia dump. Implemented using tokenisation, stemming, inverted indexes, and different degrees of relevancy. It can be used as a search framework wherever we have to deal with a huge data dump.
• Machine Learning - Sentiment Analysis from Tweets
  Implemented Sentiment Specific Word Embedding (SSWE) model in Torch. Our task is to classify tweets into Negative, Positive and Neutral. Obtain word vectors which contain both sentiment and syntactic information’s from tweets of Corpus of 10M tweets. These word vectors are used to train the SVM model and experimented on test data.
• Information Retrieval and Data Mining - Algorithm Name Detection
  Extraction of algorithm name from research papers - allows the users to list out the name of algorithms being discussed in the paper by analyzing the contents of the research document.

Here are some technical reports that I wrote :

• Fake news detection
  
• Dynamic Decision Analysis in Medical Diagnosis
  
• Medical Data Analysis
  
• Focused Crawling for extracting medical terms and Treatment methods
  
• Knowledge Base - Construction of a relational database with predefined columns from a huge text corpus using Text Mining techniques
  
• Exhaustive list of problems in Ontology Learning
  
• List of papers on Ontology Learning
  

More About Me

Here are more facts about me:

• I am interested in Entrepreneurship. It interests me because it makes me try something new. I think about solving problems and finding solutions and I build things in sparetime. Check out some of my work and experience at my LinkedIn page.

Contact

Email

sriteja ~at~ getswipe ~dot~ in