PhD · Computer Science · USF

Bhavana
Doppalapudi

Applied AI Researcher  |  NLP & Generative AI

Building intelligent systems at the intersection of research and real-world impact. My work spans large language models, agentic AI systems, and synthetic data generation — with a focus on trustworthy and deployable AI.

BD

Researcher. Builder. Problem Solver.

I am a Computer Science PhD from the University of South Florida specializing in the intersection of Artificial Intelligence, Human-Computer Interaction, and Explainable AI. While much of the AI community focuses on performance benchmarks, my research asks a different set of questions — does AI actually help people? Do users understand what its outputs mean? Do they trust it, and how does that trust shape their decisions?

My work sits at an often overlooked frontier: the behavioral and cognitive impact of AI on the people who use it. From studying how scatterplot visualizations influence trust in recommender systems, to discovering that most general users struggle to interpret visualization types beyond basic charts — my research consistently reveals that building powerful AI is only half the challenge. Making it understandable, trustworthy, and accessible to non-technical users is equally critical and far less studied.

Alongside my human-centered research, I build. I architected GenFakeNewsNet, a four-agent LLM orchestration system that produced the most challenging synthetic disinformation benchmark to date. I developed production ML forecasting systems at Amadeus IT Group and healthcare risk models at Florida Blue — bringing the same rigorous thinking I apply to research into real-world deployable systems.

I am driven by a simple belief: AI should work for everyone, not just those in tech. Safe, interpretable, and accessible AI is not a constraint on innovation — it is the standard we should be building toward.

Research Focus

Human-AI Interaction · Explainable AI · Trust & Decision-Making · Data Visualization

Publications

IEEE TVCG · Springer ISVC · TopoInVis · 5 peer-reviewed papers

Industry

Amadeus IT Group · Florida Blue · Production ML Systems

Based In

Tampa Bay Area, Florida, USA

Peer-Reviewed Work

IEEE TopoInVis · 2022 First Author

Untangling Force-Directed Layouts Using Persistent Homology

Bhavana Doppalapudi, Bei Wang, Paul Rosen · IEEE Topological Data Analysis and Visualization (TopoInVis)

Applied persistent homology principles to improve force-directed graph layouts, achieving faster convergence and higher quality node-link diagrams. Introduced new algorithms for 0- and 1-dimensional persistent homology features with interactive visualization capabilities.

Springer · ISVC 2024 First Author

Seeing Is Believing: The Role of Scatterplots in Recommender System Trust and Decision-Making

Bhavana Doppalapudi, Md Dilshadur Rahman, Paul Rosen · International Symposium on Visual Computing. Springer, Cham.

Investigated the impact of scatterplot visualizations on trust and decision-making in recommender systems through a two-part human-subject experiment. Results show that descriptive accuracy labels (high/medium/low) foster greater trust than numeric accuracy values, with significant implications for human-AI interaction design.

IEEE TVCG · 2025

A Survey on Annotations in Information Visualization: Empirical Studies, Applications and Challenges

Md Dilshadur Rahman, Bhavana Doppalapudi, Ghulam Jilani Quadri, Paul Rosen · IEEE Transactions on Visualization and Computer Graphics

A comprehensive survey examining empirical studies, real-world applications, and open challenges in the use of annotations across information visualization systems, providing a foundation for future research directions.

IEEE TVCG · 2024

A Qualitative Analysis of Common Practices in Annotations: A Taxonomy and Design Space

Md Dilshadur Rahman, Ghulam Jilani Quadri, Bhavana Doppalapudi, Danielle Albers Szafir, Paul Rosen · IEEE Transactions on Visualization and Computer Graphics

Developed a comprehensive taxonomy and design space for annotations in information visualization through qualitative analysis of common practices, providing structured guidelines for annotation design in visual analytics systems.

Journal of Tribology · 2026

The Machine Learning–Based Prediction and Experimental Validation of the Friction Performance of Recycled Brake Materials

Sai Krishna Kancharla, Bhavana Doppalapudi, Jana Kukutschová, Peter Filip · Journal of Tribology

Applied ML-based predictive modeling to forecast friction performance of recycled brake materials, validated experimentally — demonstrating the applicability of machine learning to materials science and engineering challenges.

Selected Work

Generative AI · LLMs · Agentic AI

GenFakeNewsNet

Architected a four-agent LLM orchestration system leveraging intent conditioned generation, outlet specific stylometric profiling, and paragraph level linguistic cloning to synthesize 17,400 high fidelity real/fake article pairs grounded in a 30-year, 45K article disinformation corpus. Capped 13 state-of-the-art detection models at F1 of 0.89 across 10 benchmarks. Validated through an 870 participant human study confirming a 52.7% deception rate, nearly triple the sentence replacement baseline (18.9%).

Python LangChain GPT-4o-mini Multi-Agent Orchestration LLM Fine-tuning Prompt Engineering
XAI · HCI · Recommender Systems

Trust in AI Recommender Systems

Investigated how model outputs, performance metrics, and visualizations influence user trust in AI-driven recommendations. Designed and implemented recommender systems using tree-based models across healthcare and credit datasets. Applied Bayesian Inference and Structural Equation Modeling to quantify relationships between model design choices and user behavior, demonstrating a 25% improvement in decision consistency when contextual signals accompany model outputs. Published at Springer ISVC 2024.

Python scikit-learn Classification Models Hypothesis Testing R JavaScript
Computer Vision · ML Classification

Pain Detection via Multimodal Classification

Developed a Random Forest classifier using multimodal data to detect pain in individuals with 87% accuracy, applied to identify pain signals in soldiers to mitigate risk of drug abuse. Combined emotion classification with clinical decision support objectives.

Python Random Forest Multimodal Data scikit-learn
NLP · Deep Learning

Movie Review Sentiment Analysis

Built and compared RNN and BERT-based models to predict sentiment of movie reviews, evaluating the performance gap between traditional sequential models and transformer-based architectures on real-world NLP classification tasks.

Python PyTorch BERT RNN HuggingFace

Professional Journey

Data Science Intern May 2023 – Aug 2023

Amadeus IT Group · Dallas, TX

  • Built and automated ML models for airline market size forecasting across 540K origin-destination pairs, achieving a 4–6% error rate and improving forecasting accuracy by 20% over prior methods, directly enhancing airline network scheduling and commercial strategy decisions.
  • Extracted and processed large scale air traffic data using SQL, Pandas, and NumPy, improving data quality and saving analysts 10+ hours per week in manual processing.
  • Designed automated validation frameworks and reporting pipelines that cut validation cycle time by 50% and delivered customized executive Tableau reports, accelerating decision-making for commercial stakeholders.
Data Science Intern May 2022 – Aug 2022

Amadeus IT Group · Dallas, TX

  • Built and optimized a K-means clustering model to segment airline passengers into business and leisure categories, improving market assessment accuracy by 18% and supporting data-driven revenue strategy decisions.
  • Extracted and processed large scale air traffic data using SQL, Pandas, and NumPy, reducing downstream reporting errors by 15% through robust preprocessing and data integrity pipelines.
  • Automated passenger segment validation scripts against ticket fare generators, reducing manual validation effort by 30% and accelerating time-to-insight from days to hours.
Machine Learning Specialist Oct 2018 – Dec 2018

Florida Blue · Jacksonville, FL

  • Engineered and fine-tuned a Random Forest model to predict medical outcomes for diabetic patients, achieving 94% accuracy and enabling early identification of high-risk individuals for proactive intervention.
  • Communicated model insights and proof-of-concept results to senior leadership through visualizations and executive reports, facilitating data-driven healthcare decisions.

Academic Teaching

Computer Networks Lab — Instructor of Record

Teaching Assistant · University of South Florida · [Semester, Year]

Independently delivered lab sessions, designed hands-on exercises, conducted lectures, held office hours, and managed grading for undergraduate IT students.

Introduction to Theory of Algorithms — Curriculum Design

Teaching Assistant · University of South Florida · [Semester, Year]

Designed course projects and assignments, delivered project-focused lectures, and provided mentoring and office hours support for graduate and undergraduate students.

Multi-Course Teaching Support

Teaching Assistant · University of South Florida · [Years]

Provided grading, office hours, and academic support across 8+ graduate and undergraduate courses including Operating Systems, Quantum Computing, Cloud Computing, Social Network Analysis, Computational Geometry, Computer Organization, Object-Oriented Software Design, and IT Concepts.

Community & Professional Service

Finance Chair · IEEE VIS Conference

IEEE Visualization Conference · 2023 – 2026

Managed conference budget, allocated funds across organizational committees, and prepared financial reports for one of the premier venues in visualization and visual analytics research.

Student Volunteer · IEEE VIS Conference

IEEE Visualization Conference · 2022 · Oklahoma City, OK

Supported conference operations as a student volunteer at one of the leading international venues for visualization research.

Technical Expertise

Languages

Python SQL R MySQL

LLM & Generative AI

Large Language Models LLM Fine-tuning (LoRA, PEFT) HuggingFace Transformers LangChain RAG Prompt Engineering Multi-Agent Orchestration Agentic Frameworks

Machine Learning

Supervised Learning Unsupervised Learning Ensemble Models Forecast Modeling Regression Classification Clustering scikit-learn

Deep Learning

PyTorch TensorFlow ANNs CNNs RNNs Transformers

Natural Language Processing

Tokenization Embedding Generation Intent Classification Text Preprocessing Sentiment Analysis

Statistical Analysis

Statistical Modeling Predictive Analysis Bayesian Methods Causal Inference Hypothesis Testing A/B Testing Experimental Design

Data Science

Data Mining Exploratory Data Analysis Feature Engineering Data Cleaning Data Preprocessing ETL / ELT Pipelines Large Scale Data Processing

MLOps & Deployment

MLflow Model Versioning Model Deployment Octopus Deploy CI/CD

Cloud & Infrastructure

Microsoft Azure Azure ML Azure Data Factory Azure Blob Storage HPC Clusters

Visualization & Communication

Data Visualization Tableau Matplotlib Seaborn Executive Reporting Stakeholder Communication

Tools & Platforms

Git Jupyter VS Code JavaScript

Academic Background

PhD

Doctor of Philosophy, Computer Science

University of South Florida · Tampa, FL

Graduated December 2024

Dissertation: Balancing Context and Clarity Through Visualizations for Better Decision-Making

Research Areas: Explainable AI · Data Visualization · Human-Computer Interaction · AI/ML · Generative AI · Large Language Models

MS

Master of Science, Computer Science and Engineering

University of South Florida · Tampa, FL

Graduated May 2018

BTech

Bachelor of Technology, Computer Engineering

VR Siddhartha Engineering College · Vijayawada, AP, India

Graduated April 2016

Let's Connect

Whether you're a recruiter, researcher, or collaborator — I'd love to hear from you. Open to industry roles in AI/ML and research collaborations.