Projects:
2017-Summer:

Information Sciences Institute (ISI), University of Southern California (USC)
EFFECT: Research/develop a robust big data platform to find traces of early planning activity by malicious actors, from unconventional sources including dark web and social media sites, forum discussions unstructured natural language text, structured data, and public network traffic data, and analyze these data streams to generate warnings of pending cyberattacks.

Keywords: Deep Learning/Machine Learning, Social Media Analysis, Natural Language Pro- cessing, Psychological assessment


2015: Now

Kno.e.sis Center, Computer Science & Engineering, Wright State University
Modeling Social Behavior Depression: Depression is one of the most common mental disorders in the U.S. and is the leading cause of disability affecting millions of Americans every year. Successful early identification and treatment of depression can lead to many other positive health and behavioral outcomes across the lifespan. This project will apply “big data” techniques and methods for identifying combinations of online socio-behavioral factors and neighborhood environmental conditions that can enable detection of depressive behavior in communities and studying access and utilization of healthcare services.

Keywords: Deep Learning/Machine Learning, Semi-supervised modeling, Time series anlaysis, Social Media Analysis, Natural Language Processing, Psychological assessment, Topic Modeling, Big data, Spark, Elastic Search



Fall 2016

Twitris 3.0 – Sentiment Analysis for Analyzing Presidential Election:: In this project, we utilize the state of the art deep learning and machine learning techniques to monitor/study user’s sentiment during US 2016 presidential election. This was one of the several components that allowed us to correctly predict the election outcome.

Gender-Based Violence in 140 Characters or Fewer:A #BigData Case Study of Twitter: Humanitarian and public institutions are increasingly relying on data from social media sites to measure public attitude, and provide timely public engagement. Such engagement supports the exploration of public views on important social issues such as gender-based violence (GBV). In this study, we examine Big (Social) Data consisting of nearly fourteen million tweets collected from the Twitter platform over a period of ten months to analyze public opinion regarding GBV, highlighting the nature of tweeting practices by geographical location and gender. The exploitation of Big Data requires the techniques of Computational Social Science to mine insight from the corpus while accounting for the influence of both transient events and sociocultural factors. We reveal public awareness regarding GBV tolerance and suggest opportunities for intervention and the measurement of intervention effectiveness assisting both governmental and non-governmental organizations in policy development.

Previous Projects: (University Technology Malaysia, Shiraz University)
New Implicit Opinion Mining Model For Drug Effectiveness And Side Effect Recognition In Medical Reviews.Universiti Teknologi Malaysia (UTM) Faculty of Computing, Johor, Malaysia(Vote no: R.J130000.7828.4F373, RM81000,2013-2014)

Working on understanding patient’s sentiment on online social media platforms including medical forums and studying drug effectiveness and side effect in unstructured user generated content by developing fuzzy based statistical models. Keywords: Machine Learning, Social Media Analysis, Natural Language Processing, Fuzzy Modeling, Supervised approach

3D Scanners, Stereo matching, Segmentation, 3D Reconstruction, Image processing Innovation Center of Shiraz University, Shiraz, Iran,2010-2011,