Search Articles

View query in Help articles search

Search Results (1 to 10 of 20 Results)

Download search results: END BibTex RIS


Novel Approach to Cluster Patient-Generated Data Into Actionable Topics: Case Study of a Web-Based Breast Cancer Forum

Novel Approach to Cluster Patient-Generated Data Into Actionable Topics: Case Study of a Web-Based Breast Cancer Forum

After scraping the forum data and saving into 80 files representing each forum, the files were imported into the MALLET tool. MALLET generates two tab-delimited text files as a result of algorithm execution.

Josette Jones, Meeta Pradhan, Masoud Hosseini, Anand Kulanthaivel, Mahmood Hosseini

JMIR Med Inform 2018;6(4):e45


Enhancing Seasonal Influenza Surveillance: Topic Analysis of Widely Used Medicinal Drugs Using Twitter Data

Enhancing Seasonal Influenza Surveillance: Topic Analysis of Widely Used Medicinal Drugs Using Twitter Data

The LDA method was implemented by MALLET (University of Massachusetts Amherst) [58].The number of topics retrieved for tweets about each drug was varied using an optimum topic number test as suggested by a previous method [59].

Ireneus Kagashe, Zhijun Yan, Imran Suheryani

J Med Internet Res 2017;19(9):e315


What Online Communities Can Tell Us About Electronic Cigarettes and Hookah Use: A Study Using Text Mining and Visualization Techniques

What Online Communities Can Tell Us About Electronic Cigarettes and Hookah Use: A Study Using Text Mining and Visualization Techniques

LDA is a technique that models documents as random mixtures over topics, where a topic is characterized as a distribution of words [41].We employed the LDA implementation that is available with the MALLET toolkit [42].

Annie T Chen, Shu-Hong Zhu, Mike Conway

J Med Internet Res 2015;17(9):e220


Variations in Facebook Posting Patterns Across Validated Patient Health Conditions: A Prospective Cohort Study

Variations in Facebook Posting Patterns Across Validated Patient Health Conditions: A Prospective Cohort Study

To distil the language of our sample into a smaller feature space, we used a natural language processing technique; specifically, we used an unsupervised clustering algorithm, latent Dirichlet allocation (LDA) [14] implemented in the MALLET package [15].

Robert J Smith, Patrick Crutchley, H Andrew Schwartz, Lyle Ungar, Frances Shofer, Kevin A Padrez, Raina M Merchant

J Med Internet Res 2017;19(1):e7


#Healthy Selfies: Exploration of Health Topics on Instagram

#Healthy Selfies: Exploration of Health Topics on Instagram

We used the Polylingual Topic Model implementation from MALLET [37]. The hyperparameter for the topic distribution prior (ie, “alpha”) was set to 1.0, and we used the default algorithm settings. The number of topics was set to 150.

Sachin Muralidhara, Michael J. Paul

JMIR Public Health Surveill 2018;4(2):e10150