Abstract Purpose Social media users share their ideas, thoughts, and emotions with other users. However, it is not clear how online users would respond to new research outcomes. This study aims to predict the nature of the emotions expressed by Twitter users toward scientific publications. Additionally, we investigate what features of the research articles help in such prediction. Identifying the sentiments of research articles on social media will help scientists gauge a new societal impact of their research articles. Design/methodology/approach Several tools are used for sentiment analysis, so we applied five sentiment analysis tools to check which are suitable for capturing a tweet's sentiment value and decided to use NLTK VADER and TextBlob. We segregated the sentiment value into negative, positive, and neutral. We measure the mean and median of tweets’ sentiment value for research articles with more than one tweet. We next built machine learning models to predict the sentiments of tweets related to scientific publications and investigated the essential features that controlled the prediction models. Findings We found that the most important feature in all the models was the sentiment of the research article title followed by the author count. We observed that the tree-based models performed better than other classification models, with Random Forest achieving 89% accuracy for binary classification and 73% accuracy for three-label classification. Research limitations In this research, we used state-of-the-art sentiment analysis libraries. However, these libraries might vary at times in their sentiment prediction behavior. Tweet sentiment may be influenced by a multitude of circumstances and is not always immediately tied to the paper's details. In the future, we intend to broaden the scope of our research by employing word2vec models. Practical implications Many studies have focused on understanding the impact of science on scientists or how science communicators can improve their outcomes. Research in this area has relied on fewer and more limited measures, such as citations and user studies with small datasets. There is currently a critical need to find novel methods to quantify and evaluate the broader impact of research. This study will help scientists better comprehend the emotional impact of their work. Additionally, the value of understanding the public's interest and reactions helps science communicators identify effective ways to engage with the public and build positive connections between scientific communities and the public. Originality/value This study will extend work on public engagement with science, sociology of science, and computational social science. It will enable researchers to identify areas in which there is a gap between public and expert understanding and provide strategies by which this gap can be bridged.
more »
« less
An Ensemble Deep Learning Model for Drug Abuse Detection in Sparse Twitter-Sphere
As the problem of drug abuse intensifies in the U.S., many studies that primarily utilize social media data, such as postings on Twitter, to study drug abuse-related activities use machine learning as a powerful tool for text classification and filtering. However, given the wide range of topics of Twitter users, tweets related to drug abuse are rare in most of the datasets. This imbalanced data remains a major issue in building effective tweet classifiers, and is especially obvious for studies that include abuse-related slang terms. In this study, we approach this problem by designing an ensemble deep learning model that leverages both word-level and character-level features to classify abuse-related tweets. Experiments are reported on a Twitter dataset, where we can configure the percentages of the two classes (abuse vs. non-abuse) to simulate the data imbalance with different amplitudes. Results show that our ensemble deep learning models exhibit better performance than ensembles of traditional machine learning models, especially on heavily imbalanced datasets.
more »
« less
- Award ID(s):
- 1850094
- NSF-PAR ID:
- 10123172
- Date Published:
- Journal Name:
- The 17th World Congress of Medical and Health Informatics
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The #MeToo movement is one of several calls for social change to gain traction on Twitter in the past decade. The movement went viral after prominent individuals shared their experiences, and much of its power continues to be derived from experience sharing. Because millions of #MeToo tweets are published every year, it is important to accurately identify experience-related tweets. Therefore, we propose a new learning task and compare the effectiveness of classic machine learning models, ensemble models, and a neural network model that incorporates a pre-trained language model to reduce the impact of feature sparsity. We find that even with limited training data, the neural network model outperforms the classic and ensemble classifiers. Finally, we analyze the experience-related conversation in English during the first year of the #MeToo movement and determine that experience tweets represent a sizable minority of the conversation and are moderately correlated to major events.more » « less
-
more » « less
Abstract Motivation Properties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep-learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently.
Results Here, we develop a suite of comprehensive machine-learning methods and tools spanning different computational models, molecular representations and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision–recall curves (PRCs) and receiver operating characteristic (ROC) curves. Altogether, our work not only serves as a comprehensive tool, but also contributes toward developing novel and advanced graph and sequence-learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC (area under curve) and PRC-AUC on the AI Cures open challenge for drug discovery related to COVID-19.
Availability and implementation Our source code is released as part of the MoleculeX library (https://github.com/divelab/MoleculeX) under AdvProp.
Supplementary information Supplementary data are available at Bioinformatics online.
-
Introduction The Centers for Disease Control and Prevention (CDC) spend significant time and resources to track influenza vaccination coverage each influenza season using national surveys. Emerging data from social media provide an alternative solution to surveillance at both national and local levels of influenza vaccination coverage in near real time. Objectives This study aimed to characterise and analyse the vaccinated population from temporal, demographical and geographical perspectives using automatic classification of vaccination-related Twitter data. Methods In this cross-sectional study, we continuously collected tweets containing both influenza-related terms and vaccine-related terms covering four consecutive influenza seasons from 2013 to 2017. We created a machine learning classifier to identify relevant tweets, then evaluated the approach by comparing to data from the CDC’s FluVaxView. We limited our analysis to tweets geolocated within the USA. Results We assessed 1 124 839 tweets. We found strong correlations of 0.799 between monthly Twitter estimates and CDC, with correlations as high as 0.950 in individual influenza seasons. We also found that our approach obtained geographical correlations of 0.387 at the US state level and 0.467 at the regional level. Finally, we found a higher level of influenza vaccine tweets among female users than male users, also consistent with the results of CDC surveys on vaccine uptake. Conclusion Significant correlations between Twitter data and CDC data show the potential of using social media for vaccination surveillance. Temporal variability is captured better than geographical and demographical variability. We discuss potential paths forward for leveraging this approach.more » « less
-
Background Web-based resources and social media platforms play an increasingly important role in health-related knowledge and experience sharing. There is a growing interest in the use of these novel data sources for epidemiological surveillance of substance use behaviors and trends. Objective The key aims were to describe the development and application of the drug abuse ontology (DAO) as a framework for analyzing web-based and social media data to inform public health and substance use research in the following areas: determining user knowledge, attitudes, and behaviors related to nonmedical use of buprenorphine and illicitly manufactured opioids through the analysis of web forum data Prescription Drug Abuse Online Surveillance; analyzing patterns and trends of cannabis product use in the context of evolving cannabis legalization policies in the United States through analysis of Twitter and web forum data (eDrugTrends); assessing trends in the availability of novel synthetic opioids through the analysis of cryptomarket data (eDarkTrends); and analyzing COVID-19 pandemic trends in social media data related to 13 states in the United States as per Mental Health America reports. Methods The domain and scope of the DAO were defined using competency questions from popular ontology methodology (101 ontology development). The 101 method includes determining the domain and scope of ontology, reusing existing knowledge, enumerating important terms in ontology, defining the classes, their properties and creating instances of the classes. The quality of the ontology was evaluated using a set of tools and best practices recognized by the semantic web community and the artificial intelligence community that engage in natural language processing. Results The current version of the DAO comprises 315 classes, 31 relationships, and 814 instances among the classes. The ontology is flexible and can easily accommodate new concepts. The integration of the ontology with machine learning algorithms dramatically decreased the false alarm rate by adding external knowledge to the machine learning process. The ontology is recurrently updated to capture evolving concepts in different contexts and applied to analyze data related to social media and dark web marketplaces. Conclusions The DAO provides a powerful framework and a useful resource that can be expanded and adapted to a wide range of substance use and mental health domains to help advance big data analytics of web-based data for substance use epidemiology research.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
