A5030197011- Handwritten Text Recognition Techniques
- Digital Media Forensic Detection
- Natural Language Processing Techniques
- Image Processing and 3D Reconstruction
- Digital and Traditional Archives Management
- Video Analysis and Summarization
- Software Engineering Research
- Hate Speech and Cyberbullying Detection
- Speech Recognition and Synthesis
- Digital and Cyber Forensics
- Bullying, Victimization, and Aggression
- AI in Service Interactions
- Online Learning and Analytics
- Fuzzy Logic and Control Systems
- FinTech, Crowdfunding, Digital Finance
- Cybercrime and Law Enforcement Studies
University of Maryland, College Park
2017-2025
A fundamental part of conducting cross-disciplinary web science research is having useful, high-quality datasets that provide value to studies across disciplines. In this paper, we introduce a large, hand-coded corpus online harassment data. team researchers collaboratively developed codebook using grounded theory and labeled 35,000 tweets. Our resulting dataset has roughly 15% positive examples 85% negative examples. This data useful for training machine learning models, identifying textual...
Understanding handwritten and printed text is easier for humans but computers do not have the same level of accuracy. While there are many Optical Character Recognition (OCR) tools like PyTesseract <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , Abbyy FineReader xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> which extract as digital characters from or images, none them without unrecognizable misspelled words. Spelling correction...
Graduate students at the University of Maryland's College Information Studies (UMD iSchool) collaborated in interdisciplinary teams on a case study to explore application computational methodologies datafied collections related slavery Maryland State Archives (MSA). Two research questions were examined: (1) What are opportunities and limitations for using methods open source tools characterize data encoded within records enslavement discover new patterns relationships that data? (2) How does...
Physical learning, communication, and collaboration have taken a colossal hit in 2019 2020 with cascading lockdowns resulting from the spread of COVID-19 pandemic. Virtual access has become need-of-the-hour, uses cloud-based course content delivery, distance document are becoming increasingly ubiquitous. This paper introduces novel method to allow students faculty Humanities, Arts, Social Sciences (HASS) collaborate interact through data analytical technologies using "interactive Digital...