ABSTRACT
Background: During the ongoing COVID-19 pandemic, we are being exposed to large amounts of information each day. This "infodemic" is defined by the World Health Organization as the mass spread of misleading or false information during a pandemic. This spread of misinformation during the infodemic ultimately leads to misunderstandings of public health orders or direct opposition against public policies. Although there have been efforts to combat misinformation spread, current manual fact-checking methods are insufficient to combat the infodemic. Objective: We propose the use of natural language processing (NLP) and machine learning (ML) techniques to build a model that can be used to identify unreliable news articles online. Methods: First, we preprocessed the ReCOVery data set to obtain 2029 English news articles tagged with COVID-19 keywords from January to May 2020, which are labeled as reliable or unreliable. Data exploration was conducted to determine major differences between reliable and unreliable articles. We built an ensemble deep learning model using the body text, as well as features, such as sentiment, Empath-derived lexical categories, and readability, to classify the reliability. Results: We found that reliable news articles have a higher proportion of neutral sentiment, while unreliable articles have a higher proportion of negative sentiment. Additionally, our analysis demonstrated that reliable articles are easier to read than unreliable articles, in addition to having different lexical categories and keywords. Our new model was evaluated to achieve the following performance metrics: 0.906 area under the curve (AUC), 0.835 specificity, and 0.945 sensitivity. These values are above the baseline performance of the original ReCOVery model. Conclusions: This paper identified novel differences between reliable and unreliable news articles; moreover, the model was trained using state-of-the-art deep learning techniques. We aim to be able to use our findings to help researchers and the public audience more easily identify false information and unreliable media in their everyday lives.
ABSTRACT
Background During the ongoing COVID-19 pandemic, we are being exposed to large amounts of information each day. This “infodemic” is defined by the World Health Organization as the mass spread of misleading or false information during a pandemic. This spread of misinformation during the infodemic ultimately leads to misunderstandings of public health orders or direct opposition against public policies. Although there have been efforts to combat misinformation spread, current manual fact-checking methods are insufficient to combat the infodemic. Objective We propose the use of natural language processing (NLP) and machine learning (ML) techniques to build a model that can be used to identify unreliable news articles online. Methods First, we preprocessed the ReCOVery data set to obtain 2029 English news articles tagged with COVID-19 keywords from January to May 2020, which are labeled as reliable or unreliable. Data exploration was conducted to determine major differences between reliable and unreliable articles. We built an ensemble deep learning model using the body text, as well as features, such as sentiment, Empath-derived lexical categories, and readability, to classify the reliability. Results We found that reliable news articles have a higher proportion of neutral sentiment, while unreliable articles have a higher proportion of negative sentiment. Additionally, our analysis demonstrated that reliable articles are easier to read than unreliable articles, in addition to having different lexical categories and keywords. Our new model was evaluated to achieve the following performance metrics: 0.906 area under the curve (AUC), 0.835 specificity, and 0.945 sensitivity. These values are above the baseline performance of the original ReCOVery model. Conclusions This paper identified novel differences between reliable and unreliable news articles;moreover, the model was trained using state-of-the-art deep learning techniques. We aim to be able to use our findings to help researchers and the public audience more easily identify false information and unreliable media in their everyday lives.
ABSTRACT
BACKGROUND: The COVID-19 pandemic has required triage and delays in surgical care throughout the world. The impact of these surgical delays on survival for patients with head and neck squamous cell carcinoma (HNSCC) remains unknown. METHODS: A retrospective cohort study of 37 730 patients in the National Cancer Database with HNSCC who underwent primary surgical management from 2004 to 2016 was performed. Uni- and multivariate analyses were used to identify predictors of overall survival. Bootstrapping methods were used to identify optimal time-to-surgery (TTS) thresholds at which overall survival differences were greatest. Cox proportional hazard models with or without restricted cubic splines were used to determine the association between TTS and survival. RESULTS: The study identified TTS as an independent predictor of overall survival (OS). Bootstrapping the data to dichotomize the cohort identified the largest rise in hazard ratio (HR) at day 67, which was used as the optimal TTS cut-point in survival analysis. The patients who underwent surgical treatment longer than 67 days after diagnosis had a significantly increased risk of death (HR, 1.189; 95% confidence interval [CI], 1.122-1.261; P < 0.0001). For every 30-day delay in TTS, the hazard of death increased by 4.6%. Subsite analysis showed that the oropharynx subsite was most affected by surgical delays, followed by the oral cavity. CONCLUSIONS: Increasing TTS is an independent predictor of survival for patients with HNSCC and should be performed within 67 days after diagnosis to achieve optimal survival outcomes.