arXiv subjects

Mert Can Cakmak

Publications and source records attributed to Mert Can Cakmak.

12 recordsLinked to original sources

arXiv2026

Household Movement Detection in Mixed-Format Occupancy Data Using LLM-Based Entity Resolution

Entity resolution (ER) typically relies on pairwise similarity comparisons between records, which limits its ability to capture indirect relationships present in demographic occupancy data. An important indirect pattern arises from household movement, where multiple individuals relocate together across addresses, but detecting such patterns is difficult due to mixed-format records, noise, duplication, and the absence of stable identifiers. This paper proposes an AI-enhanced framework for detecting indirect entity links associated with household movement in unstandardized name-address data. The approach integrates prompt-based large language model (LLM) named entity recognition for extracting personal names and addresses without extensive preprocessing, semantic text embeddings for robust similarity computation, and graph-based reasoning to infer group-level movement patterns. Experimental evaluation on SPX benchmark datasets (S8-S12) generated using the Synthetic Occupancy Generator demonstrates that incorporating indirect household movement evidence improves recall by 8-15% while maintaining high precision, yielding F1-score gains of 6-8% over a strong pairwise baseline.

cs.AI↗

arXiv2026

Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems

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 numerical calculation and on producing outputs that are straightforward to audit. We study synthetic payroll system as a focused, high-stakes example and evaluate whether models can understand a payroll schema, apply rules in the right order, and deliver cent-accurate results. Our experiments span a tiered dataset from basic to complex cases, a spectrum of prompts from minimal baselines to schema-guided and reasoning variants, and multiple model families including GPT, Claude, Perplexity, Grok and Gemini. Results indicate clear regimes where careful prompting is sufficient and regimes where explicit computation is required. The work offers a compact, reproducible framework and practical guidance for deploying LLMs in settings that demand both accuracy and assurance.

cs.CL↗

arXiv2026

A System for Name and Address Parsing with Large Language Models

Reliable transformation of unstructured person and address text into structured data remains a key challenge in large-scale information systems. Traditional rule-based and probabilistic approaches perform well on clean inputs but fail under noisy or multilingual conditions, while neural and large language models (LLMs) often lack deterministic control and reproducibility. This paper introduces a prompt-driven, validation-centered framework that converts free-text records into a consistent 17-field schema without fine-tuning. The method integrates input normalisation, structured prompting, constrained decoding, and strict rule-based validation under fixed experimental settings to ensure reproducibility. Evaluations on heterogeneous real-world address data show high field-level accuracy, strong schema adherence, and stable confidence calibration. The results demonstrate that combining deterministic validation with generative prompting provides a robust, interpretable, and scalable solution for structured information extraction, offering a practical alternative to training-heavy or domain-specific models.

cs.CL↗

arXiv2026

AI-Powered Multi-Stakeholder Ecosystems for Global Development: A Design Research Study on the GSI D-Hub Proof-of-Concept Platform

Digital platforms increasingly support collaboration across organizations, yet many remain constrained by fragmented data and limited transparency. This paper presents the Global Solutions Initiative (GSI) D-Hub, a data-driven coordination platform that applies explainable artificial intelligence (AI) for transparent matchmaking among deployers, solution providers, and financiers. The system integrates structured data models, interpretable algorithms, and synthetic data pipelines to reduce information asymmetries and improve data quality. Using a design-science approach, the platform was developed and validated with stakeholders from development, technology, and finance sectors. Results show that explainable recommendations and contextual dashboards enhance trust, usability, and decision confidence. The study contributes to data mining and data governance research by demonstrating how explainable, verifiable algorithms can enable scalable, trustworthy digital ecosystems for public collaboration.

cs.HC↗

arXiv2026

Case Count Metric for Comparative Analysis of Entity Resolution Results

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 processes acting on the same dataset when the true linking (labeling) is not known. The CCMS produces a set of counts that describe how the clusters produced by the first process are transformed by the second process based on four possible transformation scenarios. The transformations are that a cluster formed in the first process either remains unchanged, merges into a larger cluster, is partitioned into smaller clusters, or otherwise overlaps with multiple clusters formed in the second process. The CCMS produces a count for each of these cases, accounting for every cluster formed in the first process. In addition, when run in analysis mode, the CCMS program can assist the user in evaluating these changes by displaying the details for all changes or only for certain types of changes. The paper includes a detailed description of the CCMS process and program and examples of how the CCMS has been applied in university and industry research.

cs.DB↗

arXiv2025

Policy-Aware Generative AI for Safe, Auditable Data Access Governance

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 (LLM) to interpret natural language requests against written policies and metadata, not raw data. The system, implemented with Google Gemini~2.0 Flash, executes a six-stage reasoning framework (context interpretation, user validation, data classification, business purpose test, compliance mapping, and risk synthesis) with early hard policy gates and deny by default. It returns APPROVE, DENY, CONDITIONAL together with cited controls and a machine readable rationale. We evaluate on fourteen canonical cases across seven scenario families using a privacy preserving benchmark. Results show Exact Decision Match improving from 10/14 to 13/14 (92.9\%) after applying policy gates, DENY recall rising to 1.00, False Approval Rate on must-deny families dropping to 0, and Functional Appropriateness and Compliance Adherence at 14/14. Expert ratings of rationale quality are high, and median latency is under one minute. These findings indicate that policy constrained LLM reasoning, combined with explicit gates and audit trails, can translate human readable policies into safe, compliant, and traceable machine decisions.

cs.AI↗

arXiv2025

A Keyframe-Based Approach for Auditing Bias in YouTube Shorts Recommendations

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 content can significantly impact user exposure, especially for politically sensitive topics. In this work, we propose a keyframe-based method to audit bias and drift in short-form video recommendations. Rather than analyzing full videos or relying on metadata, we extract perceptually salient keyframes, generate captions, and embed both into a shared content space. Using visual mapping across recommendation chains, we observe consistent shifts and clustering patterns that indicate topic drift and potential filtering. Comparing politically sensitive topics with general YouTube categories, we find notable differences in recommendation behavior. Our findings show that keyframes provide an efficient and interpretable lens for understanding bias in short-form video algorithms.

cs.SI↗

arXiv2025

TriPSS: A Tri-Modal Keyframe Extraction Framework Using Perceptual, Structural, and Semantic Representations

Efficient keyframe extraction is critical for video summarization and retrieval, yet capturing the full semantic and visual richness of video content remains challenging. We introduce TriPSS, a tri-modal framework that integrates perceptual features from the CIELAB color space, structural embeddings from ResNet-50, and semantic context from frame-level captions generated by LLaMA-3.2-11B-Vision-Instruct. These modalities are fused using principal component analysis to form compact multi-modal embeddings, enabling adaptive video segmentation via HDBSCAN clustering. A refinement stage incorporating quality assessment and duplicate filtering ensures the final keyframe set is both concise and semantically diverse. Evaluations on the TVSum20 and SumMe benchmarks show that TriPSS achieves state-of-the-art performance, significantly outperforming both unimodal and prior multimodal approaches. These results highlight TriPSS' ability to capture complementary visual and semantic cues, establishing it as an effective solution for video summarization, retrieval, and large-scale multimedia understanding.

cs.CV↗

arXiv2025

Efficient Data Retrieval and Comparative Bias Analysis of Recommendation Algorithms for YouTube Shorts and Long-Form Videos

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 recommendation algorithms in shaping user experiences. These algorithms significantly influence content consumption, yet concerns about biases, echo chambers, and content diversity persist. This study develops an efficient data collection framework to analyze YouTube's recommendation algorithms for both short-form and long-form videos, employing parallel computing and advanced scraping techniques to overcome limitations of YouTube's API. The analysis uncovers distinct behavioral patterns in recommendation algorithms across the two formats, with short-form videos showing a more immediate shift toward engaging yet less diverse content compared to long-form videos. Furthermore, a novel investigation into biases in politically sensitive topics, such as the South China Sea dispute, highlights the role of these algorithms in shaping narratives and amplifying specific viewpoints. By providing actionable insights for designing equitable and transparent recommendation systems, this research underscores the importance of responsible AI practices in the evolving digital media landscape.

cs.IR↗

arXiv2025

Investigating Algorithmic Bias in YouTube Shorts

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 study investigates algorithmic bias in YouTube Shorts' recommendation system by analyzing how watch-time duration, topic sensitivity, and engagement metrics influence content visibility and drift. We focus on three content domains: the South China Sea dispute, the 2024 Taiwan presidential election, and general YouTube Shorts content. Using generative AI models, we classified 685,842 videos across relevance, topic category, and emotional tone. Our results reveal a consistent drift away from politically sensitive content toward entertainment-focused videos. Emotion analysis shows a systematic preference for joyful or neutral content, while engagement patterns indicate that highly viewed and liked videos are disproportionately promoted, reinforcing popularity bias. This work provides the first comprehensive analysis of algorithmic drift in YouTube Shorts based on textual content, emotional tone, topic categorization, and varying watch-time conditions. These findings offer new insights into how algorithmic design shapes content exposure, with implications for platform transparency and information diversity.

cs.SI↗

arXiv2025

Simulating User Watch-Time to Investigate Bias in YouTube Shorts Recommendations

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 understood. This study investigates how different viewing behaviors, including fast scrolling or skipping, influence the relevance and topical continuity of recommended videos. Using a dataset of over 404,000 videos, we simulate viewer interactions across both broader geopolitical themes and more narrowly focused conflicts, including topics related to Russia, China, the Russia-Ukraine War, and the South China Sea dispute. We assess how relevance shifts across recommendation chains under varying watch-time conditions, using GPT-4o to evaluate semantic alignment between videos. Our analysis reveals patterns of amplification, drift, and topic generalization, with significant implications for content diversity and platform accountability. By bridging perspectives from computer science, media studies, and political communication, this work contributes a multidisciplinary understanding of how engagement cues influence algorithmic pathways in short-form content ecosystems.

cs.SI↗

arXiv2025

PRISM: Perceptual Recognition for Identifying Standout Moments in Human-Centric Keyframe Extraction

Online videos play a central role in shaping political discourse and amplifying cyber social threats such as misinformation, propaganda, and radicalization. Detecting the most impactful or "standout" moments in video content is crucial for content moderation, summarization, and forensic analysis. In this paper, we introduce PRISM (Perceptual Recognition for Identifying Standout Moments), a lightweight and perceptually-aligned framework for keyframe extraction. PRISM operates in the CIELAB color space and uses perceptual color difference metrics to identify frames that align with human visual sensitivity. Unlike deep learning-based approaches, PRISM is interpretable, training-free, and computationally efficient, making it well suited for real-time and resource-constrained environments. We evaluate PRISM on four benchmark datasets: BBC, TVSum, SumMe, and ClipShots, and demonstrate that it achieves strong accuracy and fidelity while maintaining high compression ratios. These results highlight PRISM's effectiveness in both structured and unstructured video content, and its potential as a scalable tool for analyzing and moderating harmful or politically sensitive media in online platforms.

cs.CV↗