BERT Model-Based Approach For Detecting Categories of Tweets in the Field of Eating Disorders (ED)

Bení­tez-Andrades, José Alberto; Alija-Pérez, José-Manuel; García-Rodríguez, Isaías; Benavides, Carmen; Aláiz‐Moretón, Héctor; Vargas, Rafael; Garcí­a-Ordás, María Teresa

doi:10.1109/cbms52027.2021.00105

Cited by 10 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous research [17], in which 6 test-beds were conducted, the main objective was only to apply 6 pretrained bidirectional encoder representations from transformer-based models to classify a category in a data set. This time, we used a broader approach, by presenting the main problem as a comparison of the performance (accuracy and computational cost) of traditional machine learning models vs bidirectional encoder representations from transformer-based models on 4 different data categorization tasks.…”

Section: Objectivesmentioning

confidence: 99%

“…T-Hoarder allowed us to obtain additional information about tweets for further analysis, such as, ID, text, and author (among other fields). Tweets were identified by keywords [17]. In set 1 "anorexia," "anorexic," "dietary disorders," "inappetence," "feeding disorder," "food problem," "binge eating," and "anorectic" we used.…”

Section: Tweetsmentioning

confidence: 99%

“…Studies [8,9,17,[22][23][24] in the field of health informatics have used Twitter to study user behaviors and characteristics such as location, frequency, most used hashtags, or the structure of user networks. This information, being public and anonymous, is typically exempt from requiring the approval of an ethics committee [25].…”

Section: Social Media In Health Informaticsmentioning

confidence: 99%

See 2 more Smart Citations

Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)–Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

Benítez-Andrades¹,

Alija-Pérez²,

Vidal³

et al. 2022

JMIR Med Inform

View full text Add to dashboard Cite

Background Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer–based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions Bidirectional encoder representations from transformer–based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder–related tweets.

show abstract

Section: Objectivesmentioning

confidence: 99%

Section: Tweetsmentioning

confidence: 99%

Section: Social Media In Health Informaticsmentioning

confidence: 99%

See 1 more Smart Citation

Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)–Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

Benítez-Andrades¹,

Alija-Pérez²,

Vidal³

et al. 2022

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…Moreover, social media networks are utilized to promote or prevent the administration of certain interventions, e.g., in mental conditions like eating disorders [9,39]. Furthermore, Artificial Intelligence (AI) has gained momentum in the healthcare field [8,80], and AI-based solutions have been developed for disease prevention [17], pathology detection [73], and treatment prescription [57]. Analyzing the discourse on social networks such as Twitter can help to find answers to relevant problems by applying various ML techniques.…”

Section: Introductionmentioning

confidence: 99%

Empowering machine learning models with contextual knowledge for enhancing the detection of eating disorders in social media posts

Benítez-Andrades

García-Ordás

Russo

et al. 2023

View full text Add to dashboard Cite

Social networks have become information dissemination channels, where announcements are posted frequently; they also serve as frameworks for debates in various areas (e.g., scientific, political, and social). In particular, in the health area, social networks represent a channel to communicate and disseminate novel treatments’ success; they also allow ordinary people to express their concerns about a disease or disorder. The Artificial Intelligence (AI) community has developed analytical methods to uncover and predict patterns from posts that enable it to explain news about a particular topic, e.g., mental disorders expressed as eating disorders or depression. Albeit potentially rich while expressing an idea or concern, posts are presented as short texts, preventing, thus, AI models from accurately encoding these posts’ contextual knowledge. We propose a hybrid approach where knowledge encoded in community-maintained knowledge graphs (e.g., Wikidata) is combined with deep learning to categorize social media posts using existing classification models. The proposed approach resorts to state-of-the-art named entity recognizers and linkers (e.g., Falcon 2.0) to extract entities in short posts and link them to concepts in knowledge graphs. Then, knowledge graph embeddings (KGEs) are utilized to compute latent representations of the extracted entities, which result in vector representations of the posts that encode these entities’ contextual knowledge extracted from the knowledge graphs. These KGEs are combined with contextualized word embeddings (e.g., BERT) to generate a context-based representation of the posts that empower prediction models. We apply our proposed approach in the health domain to detect whether a publication is related to an eating disorder (e.g., anorexia or bulimia) and uncover concepts within the discourse that could help healthcare providers diagnose this type of mental disorder. We evaluate our approach on a dataset of 2,000 tweets about eating disorders. Our experimental results suggest that combining contextual knowledge encoded in word embeddings with the one built from knowledge graphs increases the reliability of the predictive models. The ambition is that the proposed method can support health domain experts in discovering patterns that may forecast a mental disorder, enhancing early detection and more precise diagnosis towards personalized medicine.

show abstract

“…Bidirectional Encoder Representation from Transformers (BRT) is a pre-trained language Representation model. It emphasizes the use of new Masked Language Model (MLM) instead of the traditional one-way language model or the method of shallow splicing of two one-way language models for pre-training, so that in-depth bidirectional language representation can be generated [3].…”

Section: Introductionmentioning

confidence: 99%

Emotion Analysis of Microblog Epidemic Coexistence Based on BERT

Su¹

2022

Proceedings of the 2022 2nd International Conference on Modern Educational Technology and Social Sciences (ICMETSS 2022)

View full text Add to dashboard Cite

Since the outbreak of the novel coronavirus, a large number of scholars have put forward scientific and effective analysis on epidemic prevention and control through obtaining microblog data. The spatial-temporal analysis of the evolution of public opinion on COVID-19 based on microblog data is conducive to better fight against the epidemic. In this paper, a large number of public comments on Sina Weibo in different periods of time were counted, and BERT technology was used to make emotional analysis, so as to judge whether the public attitude towards the epidemic is coexistence or zero elimination.

show abstract

BERT Model-Based Approach For Detecting Categories of Tweets in the Field of Eating Disorders (ED)

Cited by 10 publications

References 23 publications

Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)–Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)–Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

Empowering machine learning models with contextual knowledge for enhancing the detection of eating disorders in social media posts

Emotion Analysis of Microblog Epidemic Coexistence Based on BERT

Contact Info

Product

Resources

About