Results 91 to 100 of about 1,153 (163)

Exploring Problem Framing activity using BERTopic

Proceedings of the Design Society
ABSTRACT:Problem framing is a foundational aspect of the engineering design process, shaping how designers perceive challenges and potential solutions. Qualitiative methods, such as protocol analysis, have provided valuable insights about problem framing but are labor-intensive and time consuming. This study explores the use of a NLP technique BERTopic,
Gregory Litster, Emily Moore
openaire   +1 more source

LLM-Assisted Topic Reduction for BERTopic on Social Media Data

CoRR
The BERTopic framework leverages transformer embeddings and hierarchical clustering to extract latent topics from unstructured text corpora. While effective, it often struggles with social media data, which tends to be noisy and sparse, resulting in an excessive number of overlapping topics. Recent work explored the use of large language models for end-
Wannes Janssens, Matthias Bogaert, Dirk Van den Poel   +2 more
openaire   +3 more sources

Perbandingan algoritma Latent Dirichlet Allocation (LDA) dan BERTopic dalam pemodelan topik pada X [PDF]

Perbandingan algoritma Latent Dirichlet Allocation (LDA) dan BERTopic dilakukan untuk mengevaluasi efektivitas kedua metode dalam pemodelan topik pada kumpulan postingan media sosial X terkait Piala Asia U-23 2024.
Maulana, Rifky
core  

Artificial intelligence−driven analysis identifies arthroscopic shoulder surgery, meniscus injury and treatment, and total knee arthroplasty design biomechanics as the most commonly published topics in Knee Surgery, Sports Traumatology, Arthroscopy

Journal of Experimental Orthopaedics
Purpose To utilize advanced topic modelling through the Bidirectional Encoder Representations from Transformers Topic (BERTopic) model to investigate research topics in the journal Knee Surgery, Sports Traumatology, Arthroscopy (KSSTA).
Henry Baird, Prudhvi Kodali, Mauricio Gallegos, William Newton, Sarah Jenkins, Harris Slone, Michael Pullen   +6 more
doaj   +1 more source

Perceptions in 3.6 Million Web-Based Posts of Online Communities on the Use of Cancer Immunotherapy: Data Mining Using BERTopic

Journal of Medical Internet Research
BackgroundImmunotherapy has become a game changer in cancer treatment. The internet has been used by patients as a platform to share personal experiences and seek medical guidance.
Xingyue Wu, Chun Sing Lam, Ka Ho Hui, Herbert Ho-fung Loong, Keary Rui Zhou, Chun-Kit Ngan, Yin Ting Cheung   +6 more
doaj   +1 more source

BERTopic-Driven Stock Market Predictions: Unraveling Sentiment Insights

CoRR
This paper explores the intersection of Natural Language Processing (NLP) and financial analysis, focusing on the impact of sentiment analysis in stock price prediction. We employ BERTopic, an advanced NLP technique, to analyze the sentiment of topics derived from stock market comments.
Enmin Zhu, Jerome Yen
openaire   +2 more sources

Neural topic modeling with BERTopic : submodel selection factors and overall model evaluation metrics

This thesis provides insights into the BERTopic framework for topic modeling by examining sub-model selection and aims to retrieve and assess evaluation metrics specific to neural topic models developed in current literature.
Valentin, Antes
core   +2 more sources

Soil Organic Carbon Estimation via Remote Sensing and Machine Learning Techniques: Global Topic Modeling and Research Trend Exploration

Remote Sensing
Understanding and monitoring soil organic carbon (SOC) stocks is crucial for ecosystem carbon cycling, services, and addressing global environmental challenges.
Tong Li, Lizhen Cui, Yu Wu, Timothy I. McLaren, Anquan Xia, Rajiv Pandey, Hongdou Liu, Weijin Wang, Zhihong Xu, Xiufang Song, Ram C. Dalal, Yash P. Dang   +11 more
doaj   +1 more source

Evaluation of unsupervised static topic models’ emergence detection ability [PDF]

PeerJ Computer Science
Detecting emerging topics is crucial for understanding research trends, technological advancements, and shifts in public discourse. While unsupervised topic modeling techniques such as Latent Dirichlet allocation (LDA), BERTopic, and CoWords clustering ...
Xue Li, Ciro D. Esposito, Paul Groth, Jonathan Sitruk, Balazs Szatmari, Nachoem Wijnberg   +5 more
doaj   +2 more sources

Classification of TOGG Customer Complaints Using BERTopic Issue Modelling Technique

SDÜ Vizyoner Dergisi
In the study, TOGG’s 500,000 user messages are analyzed using the BERTopic topic modeling technique; the resulting data reveals that customer dissatisfaction is concentrated in financial (banking operations), technical (vehicle ınformation, software ...
Üstün Özen, Veysel Şahin, Yunus Emre Özenoğlu, Mehmet Cem Bölen   +3 more
doaj   +1 more source