Dheeman Saha

Projects

Details about various projects including "Followers Tell Who To" and others.

Followers Tell Who To

Abstract

Influencers are followed by a relatively smaller group of people on social media platforms under a common theme. Unlike global celebrities, it is challenging to categorize influencers into general categories of fame (e.g., Politics, Religion, Entertainment, etc.) because of their overlapping and narrow reach to people interested in these categories.

In this work, we focus on categorizing influencers based on their followers. We exploit the top-1K Twitter celebrities to identify the common interest among the followers of an influencer as his/her category. We annotate the top one thousand celebrities in multiple categories of popularity, language, and locations. Such categorization is essential for targeted marketing, recommending experts, etc.

We define a novel FollowerSimilarity between the set of followers of an influencer and a celebrity. We propose an inverted index to calculate similarity values efficiently. We exploit the similarity score in a K-Nearest Neighbor classifier and visualize the top celebrities over a neighborhood-embedded space.

To view the different clusters download the t-SNE image: [png] [pdf]

The labels used to identify the clusters are available here: [Labels]

The accepted paper and Github repository: [Paper] [Github]

Publications

Conference

• Saha, Dheeman, M. R. Hasan, and A. Mueen, “Followers tell who an Influencer Is” , in Proceedings of the ACM Web Conference 2023 (WWW ’23 Companion), 2023, pp. 679–687.
• F. A. Chowdhury, Saha, Dheeman, M. R. Hasan, K. Saha, and A. Mueen, “Examining factors associated with Twitter account suspension following the 2020 US presidential election” , in Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2021, pp. 607–612.
• M. R. Hasan, Saha, Dheeman, F. A. Chowdhury, J. Degnan, and A. Mueen, “Diffuscope: Inferring post-specific diffusion network” , in Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2021, pp. 407–415.
• Saha, Dheeman, L. White, U. Sekaran, S. Kumar, and S. Subramanian, “Impact of nitrogen rates and landscape position on bacterial taxa and metabolic pathways during switchgrass production,” 2019.
• Saha, Dheeman, G. Hamer, and J. Y. Lee, “Development of inter-leaves weed and plant regions identification algorithm using histogram of oriented gradient and k-means clustering” , in Proceedings of the International Conference on Research in Adaptive and Convergent Systems, 2017, pp. 136–139.
• M. Taheri, Saha, Dheeman, G. Hatfield, E. Byamukama, and S. Y. Shin, “Applied statistical model and remote sensing for a decision management system for soybean” , in Proceedings of the International Conference on Research in Adaptive and Convergent Systems, 2017, pp. 11–14.
• Saha, Dheeman, A. Hanson, and S. Y. Shin, “Development of enhanced weed detection system with adaptive thresholding and support vector machine” , in Proceedings of the International Conference on Research in Adaptive and Convergent Systems, 2016, pp. 85–88.
• Saha, Dheeman and M. A. Matin, “A new uni-scheduling algorithm in s-mac based wireless sensor networks” , in 2011 International Conference on Wireless Communications and Signal Processing (WCSP), IEEE, 2011, pp. 1–5.

Journal

• U. Sekaran, Saha, Dheeman, L. White, S. Subramanian, and S. Kumar, “Bacterial taxa and metabolic pathways influenced by nitrogen fertilization and landscape positions” , in ASA, CSSA and SSSA International Annual Meetings, ASA-CSSA-SSSA, 2020.
• Saha, Dheeman and M. A. Matin, “Low latency and energy efficient s-mac protocol for WSN: Mac protocol perspective” , International Journal of Innovative Computing, Information and Control, vol. 12, no. 03, p. 823, 2016.
• Saha, D., M. Yousuf, and M. Matin, “Energy efficient scheduling algorithm for s-mac protocol in wireless sensor network” , International Journal of Wireless & Mobile Networks, vol. 3, no. 6, p. 129, 2011.

Research Experience

• Research Assistant, Department of Computer Science

  University of New Mexico (UNM), Albuquerque, NM

  May 2020 - Present

  Internet Censorship, Privacy & Security

  Skills: Python, Matlab, Docker, Kali Linux OS

  • Developing theoretical and experimental algorithms to identify regions censoring essential Internet information by analyzing more than 450M internet traffic records from Russia.
  • Evaluating security concerns related to Personally Identifiable Information (PII) by analyzing 50M SMS records from 100k disposable phone numbers.

  Social Media Mining

  Skills: Python, Matlab, NoSQL, Docker

  • Analyzed the top 1k Twitter celebrities and identified 1.18B Twitter user IDs to categorize influencers based on their followers. (WWW'23) Repo: MicroInfluencer
  • Developed a data extraction algorithm for the DiffuScope project, inferring post-specific diffusion networks, and created a Python tool to implement the inference. (ASONAM'22, Patented)
  • Performed data extraction and developed a database to store 240M 2020 presidential election-related tweets from 21M unique users. (ASONAM'22)

• Research Assistant, Department of Computer Science

  South Dakota State University (SDSU), Brookings, SD

  July 2015 - June 2016

  Precision Agriculture

  Skills: Matlab, R, Python

  • Analyzed the impact of nitrogen fertilizer rates and landscape positions on soil microbial communities to improve nitrogen management in switchgrass production. (SSSA'20)
  • Developed a Decision Management System to detect white mold regions in soybean fields using an Autologistic Statistical Model (ASM) with 84.10% accuracy. (RACS'17)
  • Used computer vision and clustering algorithms to identify inter-leaf weed regions with 88.99% accuracy. RACS'16, RACS'17

Work Experience

• Business Analyst - Internship

  First Bank & Trust, Brookings, SD

  May 2019 - Aug 2019

  Data Modeling and Analytics

  Skills: R, Python, MySQL, Power BI

  • Developed a probabilistic model to identify and rank over 50k customer accounts, enhancing data-driven decision-making.
  • Designed and implemented a reporting portal to deliver actionable insights on 20k+ loan accounts, improving operational efficiency.

• Data Analyst - Biostatistics, Department of Plant Science

  South Dakota State University (SDSU), Brookings, SD

  Jan 2018 - Dec 2018

  Microbial Analysis

  Skills: R, Python, PICRUSt, Qiime-2 platform

  • Assessed 144 rRNA gene sequencing samples to evaluate agricultural management tactics led by Dr. Sen Subramanian.
  • Contributed to a total codebase of over 4500 lines, with nearly half of it contributed by me, on topics ranging from optimization, data analysis, plotting, etc.

• Student Programmer, Department of VP Technology and Security

  South Dakota State University (SDSU), Brookings, SD

  June 2016 - Aug 2017

  Web Application Development

  Skills: ASP.NET Framework, CSS, PHP, JavaScript, MySQL

  • Developed and optimized web forms to enhance application functionality and user experience under the leadership of Wendy Cradduck.
  • Designed and maintained databases to efficiently store and manage data related to web forms, ensuring high data integrity and seamless integration with front-end applications.

• Network Quality Associate Engineer, Department of Network Quality

  Banglalink Digital Communications Ltd. (VimpelCom), Dhaka, Bangladesh

  Aug 2013 - Aug 2014

  Network Projects Execution and Technical Reporting

  • Executed technical projects for the Core Network Department, aligning with the Technical Business Plan to optimize network performance and support business objectives.
  • Prepared and evaluated technical reports on core networks, products, and services, including Key Performance Indicators (KPIs), to support data-driven decision-making and enhance operational performance.

Contact Us