Search Articles

View query in Help articles search

Search Results (1 to 7 of 7 Results)

Download search results: CSV END BibTex RIS


A Machine Learning Approach Using Topic Modeling to Identify and Assess Experiences of Patients With Colorectal Cancer: Explorative Study

A Machine Learning Approach Using Topic Modeling to Identify and Assess Experiences of Patients With Colorectal Cancer: Explorative Study

Topic modeling, a machine learning algorithm was used to recognize patterns in the platform data. Nonnegative matrix factorization (NMF) was used as a topic modeling technique to analyze the data set and identify topics with weighted keywords [17,18]. The number of topics was determined by evaluating topic coherence scores and model stability [19,20]. Model stability was assessed using Jaccard similarity to reduce the overlap of topics.

Kelly Voigt, Yingtao Sun, Ayush Patandin, Johanna Hendriks, Richard Hendrik Goossens, Cornelis Verhoef, Olga Husson, Dirk Grünhagen, Jiwon Jung

JMIR Cancer 2025;11:e58834

An Automated Literature Review Tool (LiteRev) for Streamlining and Accelerating Research Using Natural Language Processing and Machine Learning: Descriptive Performance Evaluation Study

An Automated Literature Review Tool (LiteRev) for Streamlining and Accelerating Research Using Natural Language Processing and Machine Learning: Descriptive Performance Evaluation Study

Topic modeling allows organizing documents into clusters based on similarity and identifying abstract topics covered by similar papers. In Lite Rev, it allows the user to broaden the search strategy and get a more comprehensive and organized overview of the corpus. It can also help to quickly discard a pool of papers when searching the literature for a specific topic and significantly reduce the amount of text to verify manually.

Erol Orel, Iza Ciglenecki, Amaury Thiabaud, Alexander Temerev, Alexandra Calmy, Olivia Keiser, Aziza Merzouki

J Med Internet Res 2023;25:e39736

Public Trust in Artificial Intelligence Applications in Mental Health Care: Topic Modeling Analysis

Public Trust in Artificial Intelligence Applications in Mental Health Care: Topic Modeling Analysis

We took the coherence score as an assessment metric to evaluate how good a given topic model was and determine the optimal number of topics [46] that needed to be extracted from the user reviews. Topic coherence is a qualitative method used to score the coherence of a given topic [46]. It measures the semantic similarity between words with high scores in a topic to determine the consistency of a single topic, improving the semantic understanding of the topic [36].

Yi Shan, Meng Ji, Wenxiu Xie, Kam-Yiu Lam, Chi-Yin Chow

JMIR Hum Factors 2022;9(4):e38799

Opinion Leaders and Structural Hole Spanners Influencing Echo Chambers in Discussions About COVID-19 Vaccines on Social Media in China: Network Analysis

Opinion Leaders and Structural Hole Spanners Influencing Echo Chambers in Discussions About COVID-19 Vaccines on Social Media in China: Network Analysis

RQ3a: Do online opinion leaders and structural hole spanners tend to act as echoers or bridgers in topic dissemination? RQ3b: Do online opinion leaders and structural hole spanners tend to act as echoers or bridgers in attitude interaction? RQ4a: Do these key users acting as echoers in topic dissemination tend to play the same role in attitude interaction? RQ4b: Do these key users acting as bridgers in topic dissemination tend to play the same role in attitude interaction?

Dandan Wang, Yadong Zhou, Feicheng Ma

J Med Internet Res 2022;24(11):e40701

Getting a Vaccine, Jab, or Vax Is More Than a Regular Expression. Comment on “COVID-19 Vaccine-Related Discussion on Twitter: Topic Modeling and Sentiment Analysis”

Getting a Vaccine, Jab, or Vax Is More Than a Regular Expression. Comment on “COVID-19 Vaccine-Related Discussion on Twitter: Topic Modeling and Sentiment Analysis”

Tweets that contained any of the following keywords “vaccination,” “vaccinations,” “vaccine,” “vaccines,” “immunization,” “vaccinate,” and “vaccinated” were selected for further analysis (eg, topic modeling and sentiment analysis). I would suggest that the study might be enhanced by including additional keyword searches for vaccination synonyms identified by a method such as the Continuous Bag of Words (CBOW) word2vec model [2].

Jack Alexander Cummins

J Med Internet Res 2022;24(2):e31978

Web-Based Guidance Through Assisted Reproductive Technology (myFertiCare): Patient-Centered App Development and Qualitative Evaluation

Web-Based Guidance Through Assisted Reproductive Technology (myFertiCare): Patient-Centered App Development and Qualitative Evaluation

For example, couples can compose a topic list with questions they want to ask during their upcoming physician’s appointment. Care providers: an overview of the whole treatment team is provided through photographs, with an individual’s primary care provider on top. Users can ask medical questions to the treatment team, and they are answered within 24 hours. Forum: patients can communicate with peers on the forum. The forum is supervised by a clinician.

Ellen Marie Sparidaens, Rosella P M Hermens, Didi D M Braat, Willianne L D M Nelen, Kathrin Fleischer

J Med Internet Res 2021;23(8):e25389

COVID-19 Vaccine–Related Discussion on Twitter: Topic Modeling and Sentiment Analysis

COVID-19 Vaccine–Related Discussion on Twitter: Topic Modeling and Sentiment Analysis

We chose 16 as the topic number for our final topic model, based on two considerations: first, the topic number 16 corresponded to the highest coherence score (see Multimedia Appendix 1); second, in comparison with topics that appeared in the other topic models, the topic model with 16 topics strikes a balance between one too narrow that the model would risk excluding important topics and one so broad that it would dilute the main focus. The top 8 terms from each of the 16 topics were generated.

Joanne Chen Lyu, Eileen Le Han, Garving K Luli

J Med Internet Res 2021;23(6):e24435