Applying topic modelling and qualitative content analysis to identify and characterise ENDS product promotion and sales on Instagram

2021 ◽  
pp. tobaccocontrol-2021-056937
Author(s):  
Neal Shah ◽  
Matthew Nali ◽  
Cortni Bardier ◽  
Jiawei Li ◽  
James Maroulis ◽  
...  
Keyword(s):  
Machine Learning ◽  
Content Analysis ◽  
Qualitative Content Analysis ◽  
Topic Modelling ◽  
Unsupervised Machine Learning ◽  
Machine Learning Approach ◽  
Point Of Purchase ◽  
Social Media Platforms ◽  
Regulatory Scrutiny ◽  
Age Verification

BackgroundIncreased public health and regulatory scrutiny concerning the youth vaping epidemic has led to greater attention to promotion and sales of vaping products on social media platforms.ObjectivesWe used unsupervised machine learning to identify and characterise sale offers of electronic nicotine delivery systems (ENDS) and associated products on Instagram. We examined types of sellers, geographic ENDS location and use of age verification.MethodsOur methodology was composed of three phases: data collection, topic modelling and content analysis. We used data mining approaches to query hashtags related to ENDS product use among young adults to collect Instagram posts. For topic modelling, we applied an unsupervised machine learning approach to thematically categorise and identify topic clusters associated with selling activity. Content analysis was then used to characterise offers for sale of ENDS products.ResultsFrom 70 725 posts, we identified 3331 engaged in sale of ENDS products. Posts originated from 20 different countries and were roughly split between individual (46.3%) and retail sellers (43.4%), with linked online sellers (8.8%) representing a smaller volume. ENDS products most frequently offered for sale were flavoured e-liquids (53.0%) and vaping devices (20.5%). Online sellers offering flavoured e-liquids were less likely to use age verification at point of purchase (29% vs 64%) compared with other products.ConclusionsInstagram is a global venue for unregulated ENDS sales, including flavoured products, and access to websites lacking age verification. Such posts may violate Instagram’s policies and US federal and state law, necessitating more robust review and enforcement to prevent ENDS uptake and access.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

scholarly journals 180 The role of social constructs in placental insufficiency outcomes: an unsupervised machine learning approach

2021 ◽  
Vol 224 (2) ◽  
pp. S121-S122
Author(s):  
Ramamurthy Siripuram ◽  
Nathan R. Blue ◽  
Robert M. Silver ◽  
William A. Grobman ◽  
Uma M. Reddy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Placental Insufficiency ◽  
Learning Approach ◽  
Social Constructs ◽  
Unsupervised Machine Learning ◽  
Machine Learning Approach

scholarly journals Radiomics: a new tool to differentiate adrenocortical adenoma from carcinoma

BJS Open ◽  
2021 ◽  
Vol 5 (1) ◽  
Author(s):  
F Torresan ◽  
F Crimì ◽  
F Ceccato ◽  
F Zavan ◽  
M Barbot ◽  
...  
Keyword(s):  
Machine Learning ◽  
Imaging Techniques ◽  
Second Order ◽  
Learning Approach ◽  
Adrenocortical Adenoma ◽  
Unsupervised Machine Learning ◽  
First Order ◽  
Main Challenge ◽  
Machine Learning Approach ◽  
Adrenocortical Tumours

Abstract Background The main challenge in the management of indeterminate incidentally discovered adrenal tumours is to differentiate benign from malignant lesions. In the absence of clear signs of invasion or metastases, imaging techniques do not always precisely define the nature of the mass. The present pilot study aimed to determine whether radiomics may predict malignancy in adrenocortical tumours. Methods CT images in unenhanced, arterial, and venous phases from 19 patients who had undergone resection of adrenocortical tumours and a cohort who had undergone surveillance for at least 5 years for incidentalomas were reviewed. A volume of interest was drawn for each lesion using dedicated software, and, for each phase, first-order (histogram) and second-order (grey-level colour matrix and run-length matrix) radiological features were extracted. Data were revised by an unsupervised machine learning approach using the K-means clustering technique. Results Of operated patients, nine had non-functional adenoma and 10 carcinoma. There were 11 patients in the surveillance group. Two first-order features in unenhanced CT and one in arterial CT, and 14 second-order parameters in unenhanced and venous CT and 10 second-order features in arterial CT, were able to differentiate adrenocortical carcinoma from adenoma (P < 0.050). After excluding two malignant outliers, the unsupervised machine learning approach correctly predicted malignancy in seven of eight adrenocortical carcinomas in all phases. Conclusion Radiomics with CT texture analysis was able to discriminate malignant from benign adrenocortical tumours, even by an unsupervised machine learning approach, in nearly all patients.

COVID-19 and Vitamin D Misinformation on YouTube: A Content Analysis (Preprint)

2021 ◽  
Author(s):  
Emma Kathleen Quinn ◽  
Shelby Fenton ◽  
Chelsea A. Ford-Sahidzada ◽  
Andrew Harper ◽  
Alessandro R. Marcon ◽  
...  
Keyword(s):  
Vitamin D ◽  
Content Analysis ◽  
Health Information ◽  
Qualitative Content Analysis ◽  
Health Behaviours ◽  
Medical Professionals ◽  
Solar Ultraviolet Radiation ◽  
Ultraviolet Radiation Exposure ◽  
Social Media Platforms ◽  
Solar Uv

BACKGROUND The “infodemic” accompanying the SARS-CoV-2 virus pandemic has the potential to increase avoidable spread as well as engagement in risky health behaviours. While social media platforms such as YouTube can be an inexpensive and effective method of sharing accurate health information, inaccurate and misleading information shared on YouTube can be dangerous for viewers [1]. OBJECTIVE The confusing nature of data and claims surrounding the benefits of vitamin D, particularly in the prevention or cure of COVID-19, influences both viewers and the general “immune boosting” commercial interest. METHODS YouTube video results for the search terms COVID, coronavirus, and vitamin D were collected and analyzed for content themes and deemed useful or misleading, based on the accuracy or inaccuracy of the content. Qualitative content analysis and simple statistical analysis were used to determine the prevalence and frequency of concerning content, such as confusing correlation with causation regarding vitamin D benefits. RESULTS 77 videos with 10,225,763 views (at the time of data collection) were included in the analysis, with over three quarters of them containing misleading content about COVID-19 and vitamin D. 58% of the videos confused the relationship between vitamin D and COVID-19, with 85% of the videos stating that vitamin D had preventative or curative abilities. The major contributor of these videos were medical professionals with YouTube accounts. Vitamin D recommendations that do not align with current literature were frequently suggested, included taking over the recommended safe dosage or seeking intentional solar ultraviolet radiation exposure. CONCLUSIONS The spread of misinformation is particularly alarming when spread by medical professionals and confusion of existing data suggesting vitamin D has “immune boosting” abilities can add to viewer confusion or mistrust in health information. Further, the suggestions made in the videos may increase risks of other poor health outcomes, such as skin cancer from solar UV radiation.

Supervised and Unsupervised Machine Learning Approach in Facies Prediction

2020 ◽  
Author(s):  
Daniel Oluwadara Fadokun ◽  
Ishioma Bridget Oshilike ◽  
Mike Obi Onyekonwu
Keyword(s):  
Machine Learning ◽  
Learning Approach ◽  
Unsupervised Machine Learning ◽  
Machine Learning Approach

scholarly journals Degrees of Freedom: Exploring Agency, Narratives, and Technological Affordances in the #TakeAKnee Controversy

2019 ◽  
Vol 5 (2) ◽  
pp. 205630511982612 ◽  
Author(s):  
Judith E. Rosenbaum
Keyword(s):  
Social Media ◽  
Content Analysis ◽  
Degrees Of Freedom ◽  
Qualitative Content Analysis ◽  
Structuration Theory ◽  
The Social ◽  
American National Identity ◽  
Social Media Platforms ◽  
Media Narratives ◽  
Technological Affordances

This study extends current research into social media platforms as counterpublic spaces by examining how the social media narratives produced by the #TakeAKnee controversy negotiate technological affordances and existing discourses surrounding American national identity. Giddens’ Structuration Theory is used to explore the nature of user agency on social media platforms and the extent to which this agency is constrained or enabled by the interplay between the systems and structures that guide social media use. Exploratory qualitative content analysis was used to analyze and compare tweets and Instagram posts using the #TakeAKnee hashtag shared in September 2017. Results showed that narratives are dominated by four themes, freedom, unity, equality and justice, and respect and honor. Users actively employ technological affordances to create highly personalized meanings, affirming that agency operates at the intersection of reflexivity and self-efficacy.

Sign in / Sign up

Export Citation Format

Share Document