Social Media Utilization among Dental Practitioner in Riyadh, Saudi Arabia

Pretrained Transformer Language Models Versus Pretrained Word Embeddings for the Detection of Accurate Health Information on Arabic Social Media: Comparative Study

Background

In recent years, social media has become a major channel for health-related information in Saudi Arabia. Prior health informatics studies have suggested that a large proportion of health-related posts on social media are inaccurate. Given the subject matter and the scale of dissemination of such information, it is important to be able to automatically discriminate between accurate and inaccurate health-related posts in Arabic.

Objective

The first aim of this study is to generate a data set of generic health-related tweets in Arabic, labeled as either accurate or inaccurate health information. The second aim is to leverage this data set to train a state-of-the-art deep learning model for detecting the accuracy of health-related tweets in Arabic. In particular, this study aims to train and compare the performance of multiple deep learning models that use pretrained word embeddings and transformer language models.

Methods

We used 900 health-related tweets from a previously published data set extracted between July 15, 2019, and August 31, 2019. Furthermore, we applied a pretrained model to extract an additional 900 health-related tweets from a second data set collected specifically for this study between March 1, 2019, and April 15, 2019. The 1800 tweets were labeled by 2 physicians as accurate, inaccurate, or unsure. The physicians agreed on 43.3% (779/1800) of tweets, which were thus labeled as accurate or inaccurate. A total of 9 variations of the pretrained transformer language models were then trained and validated on 79.9% (623/779 tweets) of the data set and tested on 20% (156/779 tweets) of the data set. For comparison, we also trained a bidirectional long short-term memory model with 7 different pretrained word embeddings as the input layer on the same data set. The models were compared in terms of their accuracy, precision, recall, F₁ score, and macroaverage of the F₁ score.

Results

We constructed a data set of labeled tweets, 38% (296/779) of which were labeled as inaccurate health information, and 62% (483/779) of which were labeled as accurate health information. We suggest that this was highly efficacious as we did not include any tweets in which the physician annotators were unsure or in disagreement. Among the investigated deep learning models, the Transformer-based Model for Arabic Language Understanding version 0.2 (AraBERTv0.2)-large model was the most accurate, with an F₁ score of 87%, followed by AraBERT version 2–large and AraBERTv0.2-base.

Conclusions

Our results indicate that the pretrained language model AraBERTv0.2 is the best model for classifying tweets as carrying either inaccurate or accurate health information. Future studies should consider applying ensemble learning to combine the best models as it may produce better results.

Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

This paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F₁ score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F₁ score of 75.2% and accuracy of 90.7% compared to F₁ score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

The role of Twitter in dental education: A systematic review

BACKGROUND

The rapid growth of social media in recent years has highlighted uses beyond their original purposes, particularly in education. Twitter is a free, open access social network with high potential to enhance interactive learning. The use of Twitter in dental education has been far less investigated; therefore, the objective of this systematic review is to explore the current uses and to examine the impact of Twitter on dental education, and to analyze and predict potential models of Twitter for future application in dental training, education, and teaching.

METHODS

Five databases (PubMed, Embase, Medline, Scopus, and Web of Science) and the gray literature using keywords related to Twitter and dental education were searched. Articles were screened for inclusion, and two researchers independently extracted the data using a standardized data collection template and analyzed the quality of the included articles using the Medical Education Research Study Quality Instrument.

RESULTS

Of the 121 articles identified from the initial search, 68 remained after duplications were removed. Article screening removed 61 articles leaving 7 eligible for inclusion and data extraction. Five studies were cross-sectional and two were cohort studies, and all involved survey-based designs with 998 respondents in total. Quality assessment gave a score range between 8 and 12.5 out of a total of 18 points.

CONCLUSIONS

Our study supports the potential for Twitter as a useful learning tool in dental education. Features, including the open access nature of Twitter as well as the low level of ads and free registration, make it appealing to students as well as a useful tool for interactive learning. However, there are significant barriers to its use, including privacy and concerns about professionalism. Higher quality and greater impact research is required.

Insights on Using Social Media in Dental Education: A Cross-Sectional Study in Saudi Arabia

Objective:

The purpose of this study is to investigate the insight of utilizing social media as an educational tool among dental faculty members in Saudi Arabia.

Methods:

A descriptive cross-sectional survey was distributed to 380 randomly selected faculty members from three governmental universities in the Western region of Saudi Arabia. The participants completed a validated questionnaire to assess the intent of using social media and their opinion about the benefits and drawbacks of adopting social media as an educational tool. Descriptive statistics and chi-square test were used to analyse the results.

Results:

Out of 380 faculty members who were invited to participate, 271 responded (71% response rate). Results reveal that WhatsApp, followed by YouTube, Facebook, and Twitter were the mostly used social media platforms. Around 31% of the participants reported using social media for ten hours or more. The main reason reported by the participants for using social media was searching for information (82.17%), followed by professional networking (78.29%) and learning (75.97%). The majority of the participants agreed that social media have advantages like it helps students to communicate and share ideas with instructors, update students with new resources, and improve students’ skills. Social media also has several disadvantages; the respondents believe that it can increase their addictive potential, create more demand for internet access, and raise concerns on direct contact with students.

Conclusion:

As an educational tool, social media can enrich the teaching experience by using the appropriate strategies. The findings may be useful for educators to adopt social media platforms in dental education.