11 papers
Household Movement Detection in Mixed-Format Occupancy Data Using LLM-Based Entity Resolution
Sasirekha Oguri, John R. Talburt, Mert Can Cakmak
Entity resolution (ER) typically relies on pairwise similarity comparisons between records, which limits its ability to capture indirect relationships present in demographic occupa…
AI-Powered Multi-Stakeholder Ecosystems for Global Development: A Design Research Study on the GSI D-Hub Proof-of-Concept Platform
Muzakkiruddin Ahmed Mohammed, Adeeba Tarannum, Eileen Devereux Dailey +3
Digital platforms increasingly support collaboration across organizations, yet many remain constrained by fragmented data and limited transparency. This paper presents the Global S…
Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems
Hendrika Maclean, Mert Can Cakmak, Muzakkiruddin Ahmed Mohammed +2
Large language models are now used daily for writing, search, and analysis, and their natural language understanding continues to improve. However, they remain unreliable on exact…
A System for Name and Address Parsing with Large Language Models
Adeeba Tarannum, Muzakkiruddin Ahmed Mohammed, Mert Can Cakmak +2
Reliable transformation of unstructured person and address text into structured data remains a key challenge in large-scale information systems. Traditional rule-based and probabil…
Case Count Metric for Comparative Analysis of Entity Resolution Results
John R. Talburt, Muzakkiruddin Ahmed Mohammed, Mert Can Cakmak +4
This paper describes a new process and software system, the Case Count Metric System (CCMS), for systematically comparing and analyzing the outcomes of two different ER clustering…
Policy-Aware Generative AI for Safe, Auditable Data Access Governance
Shames Al Mandalawi, Muzakkiruddin Ahmed Mohammed, Hendrika Maclean +2
Enterprises need access decisions that satisfy least privilege, comply with regulations, and remain auditable. We present a policy aware controller that uses a large language model…
A Keyframe-Based Approach for Auditing Bias in YouTube Shorts Recommendations
Mert Can Cakmak, Nitin Agarwal
YouTube Shorts and other short-form video platforms now influence how billions engage with content, yet their recommendation systems remain largely opaque. Small shifts in promoted…
Efficient Data Retrieval and Comparative Bias Analysis of Recommendation Algorithms for YouTube Shorts and Long-Form Videos
Selimhan Dagtas, Mert Can Cakmak, Nitin Agarwal
The growing popularity of short-form video content, such as YouTube Shorts, has transformed user engagement on digital platforms, raising critical questions about the role of recom…
Investigating Algorithmic Bias in YouTube Shorts
Mert Can Cakmak, Nitin Agarwal, Diwash Poudel
The rapid growth of YouTube Shorts, now serving over 2 billion monthly users, reflects a global shift toward short-form video as a dominant mode of online content consumption. This…
Simulating User Watch-Time to Investigate Bias in YouTube Shorts Recommendations
Selimhan Dagtas, Mert Can Cakmak, Nitin Agarwal
Short-form video platforms such as YouTube Shorts increasingly shape how information is consumed, yet the effects of engagement-driven algorithms on content exposure remain poorly…
TriPSS: A Tri-Modal Keyframe Extraction Framework Using Perceptual, Structural, and Semantic Representations
Mert Can Cakmak, Nitin Agarwal, Diwash Poudel
Efficient keyframe extraction is critical for video summarization and retrieval, yet capturing the full semantic and visual richness of video content remains challenging. We introd…