Expanding Our Understanding of COVID-19 from Biomedical Literature Using Word Embedding

Yang, Heyoung; Sohn, Eunsoo

doi:10.3390/ijerph18063005

Cited by 2 publications

References 23 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

What are we learning with Yoga: a text mining approach to literature

Raittz

Pierri

Perico

et al. 2022

Preprint

View full text Add to dashboard Cite

Techniques used in yoga existed long before science as we know it. However, with Yoga westernization, the proliferation of scientific studies addressing the subject is exponential. Even though the literature presents thousands of related articles, many studies are considered flimsy - the diversity of methods, areas of interest, and focus cause it to become a complex environment without general guidelines for the researcher. This status may represent one of the impediments to the field's evolution. This study aims to elaborate a global structure of the literature on Yoga to open the door for multidisciplinary collaboration and bring new light to some relevant aspects. Due to its complexity, we understand that techniques to model complex domains are necessary. Contemporary methods of Artificial Intelligence have promoted advances in Bioinformatics, including text mining to scientific literature. Through the vector representation of texts, we got semantic abilities and could organize data in a way that allowed us to acquire a global vision of this literature. Additionally, we made the platforms available to Yoga researchers to enable them to evaluate our findings and make their forays into the literature. Besides better understanding why we study Yoga, we discovered that the literature offers insights into the relationships in broader aspects.

show abstract

What are we learning with Yoga: a text mining approach to literature

Raittz

Pierri

Perico

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

User Representation Learning for Social Networks: An Empirical Study

Hallac

Aydın

2021

Applied Sciences

View full text Add to dashboard Cite

Gathering useful insights from social media data has gained great interest over the recent years. User representation can be a key task in mining publicly available user-generated rich content offered by the social media platforms. The way to automatically create meaningful observations about users of a social network is to obtain real-valued vectors for the users with user embedding representation learning models. In this study, we presented one of the most comprehensive studies in the literature in terms of learning high-quality social media user representations by leveraging state-of-the-art text representation approaches. We proposed a novel doc2vec-based representation method, which can encode both textual and non-textual information of a social media user into a low dimensional vector. In addition, various experiments were performed for investigating the performance of text representation techniques and concepts including word2vec, doc2vec, Glove, NumberBatch, FastText, BERT, ELMO, and TF-IDF. We also shared a new social media dataset comprising data from 500 manually selected Twitter users of five predefined groups. The dataset contains different activity data such as comment, retweet, like, location, as well as the actual tweets composed by the users.

show abstract

Expanding Our Understanding of COVID-19 from Biomedical Literature Using Word Embedding

Cited by 2 publications

References 23 publications

What are we learning with Yoga: a text mining approach to literature

What are we learning with Yoga: a text mining approach to literature

User Representation Learning for Social Networks: An Empirical Study

Contact Info

Product

Resources

About