Search Results

You are looking at 1 - 6 of 6 items for :

  • "Dirichlet" x
  • Refine by Access: All Content x
Clear All
Restricted access

Are Sport Consumers Unique? Consumer Behavior Within Crowded Sport Markets

Hunter Fujak, Stephen Frawley, Heath McDonald, and Stephen Bush

leagues compete. This is achieved by adopting Ehrenberg’s ( 1971 ) well-established framework of buyer behavior within repeat-purchase markets, utilizing the negative binomial distribution (NBD) Dirichlet model of market analysis ( Bassi, 2011 ). The core research purpose therefore is to understand sport

Restricted access

Big Data and Innovative Research Methods

Yoseph Z. Mamo

Championship League final match ( Yan et al., 2019 ). For example, Yoo et al. ( 2022 ) utilized latent Dirichlet allocation topic modeling to compare news coverage of the Paralympics from the United States and South Korea. More specifically, it has been shown that NLP can help managers make data

Restricted access

Machine Learning in Sport Social Media Research: Practical Uses and Opportunities

James Du, Yoseph Z. Mamo, Carter Floyd, Niveditha Karthikeyan, and Jeffrey D. James

ML-based NLP technique has the flexibility to combine text embeddings and clustering algorithms to handle both structured and unstructured text data and outperforms alternative topic models (e.g., Latent Dirichlet Analysis, Latent Semantic Analysis, and nonnegative matrix factorization) by

Restricted access

“We Are All Broncos”: Hockey, Tragedy, and the Formation of Canadian Identity

Liam Kennedy, Derek Silva, Madelaine Coelho, and William Cipolli III

hashtag in Figure  3 . Finally, relying on machine learning architecture and Natural Language Processing (NLP), we used latent Dirichlet allocation (LDA) to generate statistical models that help separate large bodies of text into small groups of similar topics ( Blei, Ng, & Jordan, 2003 ). This enabled us

Restricted access

Power and Trust Dynamics of Sexual Violence: A Textual Analysis of Nassar Victim Impact Statements and #MeToo Disclosures on Twitter

Brian A. Eiler, Rosemary Al-Kire, Patrick C. Doyle, and Heidi A. Wayment

to textual analysis than bag-of-word approaches (e.g., LIWC), other techniques such as topic modeling, latent semantic analysis, latent Dirichlet analysis, or other supervised machine learning approaches may provide more nuanced insight. Third, our research did not differentiate between different

Free access

The Potential Impact of Physical Activity on the Burden of Osteoarthritis and Low Back Pain in Australia: A Systematic Review of Reviews and Life Table Analysis

Mary Njeri Wanjau, Holger Möller, Fiona Haigh, Andrew Milat, Rema Hayek, Peta Lucas, and J. Lennert Veerman

METs, and vigorous PA = 7.5 METs). 18 PA was modeled as a categorical approximation of a Dirichlet distribution, a generalization of the Beta distribution to multiple categories. 19 For the model, PA was categorized into 4 levels: inactive (0 MET), low active (>0 and <600 MET-min/wk), moderately