Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 39 for “"BERTopic"”.
-
Temporal evolution of aviation safety topics: comparing Sructural Topic Modeling and BERTopic on FAA Service Difficulty Reports
… from Transformers (BERT) for topic modeling (BERTopic) and Structural Topic Model (STM), offer promising approaches for analyzing aviation safety data. More specifically, these methods can identify emerging safety trends and potential risks by tracking how incident report topics evolve over …
-
LLMusic : modelagem de tópicos em letras de músicas combinando LLM, engenharia de prompt e BERTopic - estudo de caso no funk brasileiro
… que integra LLMs, Engenharia de Prompt (EP) e BERTopic. O LLMusic funciona em duas etapas principais: (i) identificação de tópicos, utilizando LLMs para sintetizar trechos de letras em temas centrais e posteriormente agrupá-los em tópicos usando BERTopic; e (ii) classificação em tópicos, na …
-
Demographic and Geographic Drivers of Scientific Trends: Covariate Effects in Canadian NSERC Proposals
… Topic Modeling (STM), and transformer-based BERTopic. A key innovation is the COFFEE pipeline, a novel Python tool that enables robust covariate effect estimation for BERTopic. This advancement addresses a significant gap, as BERTopic lacks a native function for covariate analysis, unlike the …
-
A Comparison of Unsupervised Topic Modelling Techniques for Qualitative Data Analysis of Online Communities
… issue, this thesis explores the integration of BERTopic, an advanced Large Language Model (LLM)-based method, into the Computational Thematic Analysis (CTA) Toolkit to support qualitative data analysis of social media. We conducted interviews and hands-on evaluations in which qualitative …
-
Machine learning based narrative search in the information space /
… using two algorithmic topic modeling approaches: BERTopic and ANTM, which combine embeddings, dimensionality reduction, clustering and narrative extraction using Large Language Models (LLMs). The research also explores LLMs based evaluation metrics for measuring topic model performance. Key …
-
Natural Language Processing for Education Research: Exploring Strategic Use of Traditional and Large Language Topic Models
… (LDA), Non-Negative Matrix Factorization (NMF), BERTopic with MiniLM and MPNet sentence embeddings, and zero-shot classification (ZSC). Performance was evaluated using accuracy, macro and weighted F1, topic coherence, and inter-rater reliability (Cohen’s κ). Ground truth was established by two …
-
Bike Lane-Involved Crash Severity: An Analysis of Heterogeneity, Temporal Stability, and Policy Implications
… SHapley Additive exPlanations (SHAP), and BERTopic-based crash narrative analysis. These methods are applied across three severity outcomes: no injury, possible or non-incapacitating injury, and fatal or incapacitating injury. Results indicate that lighting conditions, roadway context, and …
-
Beyond the Plastic Facade: Unveiling the Multifaceted Discourse and Impact of Barbie in Film
… language processing techniques. Employing BERTopic for topic modeling, I analyzed conversations embedded in YouTube comments from Warner Bros.'s own promotional content as well as third-party YouTube content pre- and post- the film’s release to unearth the themes and sentiments associated …
-
A Framework for Reliable Domain AI: Knowledge-Grounded Data and Logic-Graph Reasoning
… more coherent topics than LDA, k-means, and BERTopic, and topic-guided sampling under fixed labeling budgets of 10%, 20%, and 40% consistently improves downstream sentiment-classification accuracy and macro-F1 over random and BERTopic-based sampling. Second, we propose a two-stage logic-graph …
-
RETHINKING INDUSTRY CLASSIFICATION: LEVERAGING LLMS FOR MULTI-VIEW AND MULTI-LABEL APPROACHES
… industries. The resulting assignments outperform BERTopic and LDA baselines in predictive validity and better balance grouping similar firms with separating dissimilar firms. Together, the studies demonstrate how LLM-based text processing and graph methods can improve peer benchmarking, investment …
-
Misogyny and Extremism Across Forums, Podcasts, and Manifestos: A Mixed-Methods Study
… into epistemic “truths.” Using topic modeling (BERTopic) alongside qualitative discourse analysis, this study identifies recurring patterns of biologized rejection, misogynistic dehumanization, and glorified violence. Incel ideology is conceptualized as an affective epistemology: a system in …
-
Scientific and Technological Convergence in AI: From Data-Driven Science to Medical Applications
… communities via modularity optimization, while BERTopic was used to extract semantic topics within each community. Pathway analysis quantified the temporal evolution of these communities using overlap metrics to capture the dynamics of convergence over time. Our analysis shows that scientific …
-
Exploring LLM Integration and Its Influence on Agent Behavior and Productivity in Insurance Call Centers
… sentiment analysis, part-of-speech tagging, and BERTopic modeling. These methods helped us identify changes in language use and communication style before and after the introduction of AI support tools. Our findings suggest that agents in call centers adapt their communication to become more …
-
NATURAL LANGUAGE PROCESSING, SOCIAL MEDIA, AND EPIDEMIC MODEL-ING FOR WILDFIRE RESPONSE AND RE-SILIENCE ENHANCEMENT
… tools. To address this, we integrated the BERTopic and SIR models to capture public responses on Twitter during the 2020 western U.S. wildfire season, analyzing both the magnitude and velocity of topic diffusion. The results displayed a clear relationship between topic trends and wildfire …
-
Topic Modeling for Heterogeneous Digital Libraries: Tailored Approaches Using Large Language Models
… NeuralLDA, Contextualized Topic Models, and BERTopic. Finally, we integrated Large Language Models (LLMs), such as GPT-4, using prompt engineering to augment traditional topic models, refining and interpreting their outputs without replacing them. The framework was tested on a large corpus of …
-
Product Design For Repairability: Identifying Failure Modes With Topic Modeling And Designing For Electronic Waste Reuse
… Non-Negative Matrix Factorization (NMF) and BERTopic approaches are used to analyze 5,000 Amazon reviews for standalone computer keyboards to assess device failure modes. The proposed method identifies several failure modes for keyboards, including keys sticking, legs breaking, keyboards …
-
Narratives for Sale: Conceptualizing and Measuring the Marketplace for Consumer Chatter in a Digital World
… (MCC Analysis Framework), which builds on BERTopic, a state-of-the-art topic modeling framework, combining it with hierarchical clustering approaches to systematically analyze large-scale consumer-generated content. This framework allows for the identification of key thematic structures …
-
From understanding to repair : an empirical and agentic investigation of Ruby developer challenges
… through a survey of 154 developers. Using BERTopic for topic modeling, GPT-4o for taxonomy construction, and human validation, we identify a three-level hierarchy of 35 topics, 18 middle categories, and six main categories of Ruby challenges. The results reveal that web application …
-
Understanding the perceptions and challenges of large language models through social and technical lenses
… surveys. Leveraging NLP techniques such as BERTopic and RoBERTa for sentiment and topic modeling, I conduct thematic analysis through a multi-phased approach with a specific taxonomy developed using Stack Overflow. I use Twitter to understand general user opinions, Stack Overflow to extract …
Page 1 of 2