Covid-19 in the news this week
- Biotron receives positive FDA guidance for Covid-19 drug trial
- U.S. Doctors Reconsider Pfizer’s Paxlovid for Lower-Risk COVID Patients
- Yale study shows no link between COVID-19 vaccines and infertility
- Study shows cell membrane-bound enzyme is essential for COVID-19 infection
- Researchers evaluate atovaquone as a COVID-19 treatment
- Direct comparison of immune memory responses to four COVID-19 vaccines
- AcadeMab develops therapy for COVID-19 Omicron variant with potent neutralizing efficacy
- FDA grants three-month extension on expiration dates on iHealth tests
- Omicron Subvariant Now Responsible for Nearly 60% of U.S. COVID Cases
- During the Omicron Wave, Death Rates Soared for Older People
- Moderna delays COVID vaccine deliveries to EU by several months
- COVID-19 vaccines for the youngest children may be approved in two weeks
- Pfizer’s Paxlovid reduces COVID risk in seniors regardless of vaccine status -study
- Immune modulator drugs improved survival for people hospitalized with COVID-19
- COVID-19 Vaccination Associated with Higher Incidence of DLLR in Women
- Study finds vaccines are 90% effective against severe COVID-19 for up to six months
- Vaccination lowers the risk of experiencing severe COVID-19 in dialysis patients
DrugVisual Covid-19 links
Net daily sentiment ranged from -43.49 for Remdesivir on Monday the 30th to 25.79 for Monoclonal antibodies on Sunday the 29th.
The sentiment for each tweet is scored from -1 (most negative) to +1 (most positive) using VADER sentiment analysis. Net sentiment is calculated by summing the sentiment across all tweets for a given day and/or category, then normalizing the score by the number of tweets.
Medical conditions from the MedDRA dictionary
Infection was the most frequently observed medical condition mentioned. Fear had the highest overall net sentiment of 33.15. Overweight had the lowest net sentiment this week (-88.58).
MedDra is a standardized medical terminology developed by the International Council for Harmonization Cross-referencing tweets against this list is a starting point for identifying medical conditions mentioned in tweets.
Cross-referencing the MedDRA dictionary by sentiment and topic
There were 136 tweets with an strong positive sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Infection, (2) Fear, (3) Blindness, Blind, (4) Flu, (5) Lung infection, (6) Confused, Confusion, (7) Fever, (8) Rigors, (9) Sickness, (10) Anxiety. Of these terms, Lung infection (n=6), Confused, Confusion (n=4), Fever (n=4), Rigors (n=4), Anxiety (n=3) were not in the top 10 most frequent terms across all tweets.
There were 256 tweets with an strong negative sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Overweight, (2) Sickness, (3) Flu, (4) Infection, (5) Heart attack, (6) Cancer, (7) Pain, (8) Blindness, Blind, (9) Coldness, Cold, (10) Pneumonia. Of these terms, Pneumonia (n=8) were not in the top 10 most frequent terms across all tweets.
The 25 most important words within positive tweets (compared to negative and neutral) tweets are shown in the treemap below. The size of each box represents the weighted score of each word. The word “j” within the search for “Pfizer vaccine” had the highest overall weight. When the words are summed for each topic, Pfizer vaccine had the highest overall weight.
The 25 most important words within negative tweets (compared to positive and neutral) tweets are shown in the treemap below. The word “die” within the search for “Pfizer vaccine” had the highest overall weight. When the words are summed for each topic, “Moderna vaccine” had the highest overall weight within negative tweets.
This analysis of words evaluates the stemmed version of words using the Snowball algorithm. By stemming words, words with similar meaning, such as pain, painful & pained, are grouped together as simply “pain”.
Beta: text classification
Tweets that describe adverse events/side effects (first person point of view)
|tweet||search topic(s)||medical condition(s) mentioned|
|Enough of this hysteria!!
I took the Pfizer vaccine and all that happened was my lymph node under my right arm turned into a golf ball, and my front teeth fell out.
Other than that Im frickin fine.
|I wish you a speedy recovery Governor. I got the monoclonal antibodies infusion. You may feel very tired after COVID. I got some brain fog from it. It feels like recovering from pneumonia. Sleep and relax.||monoclonal antibodies||Pneumonia|
|I had a short term reaction to all 3 <U+0001F489> vaccine (hives, mild numbness from outer right shoulder to tip of right little finger) prescribed Prednisolone 25mg by my GP. Worked quickly.. After a covid coughing fit I took the steroid, worked the same, <U+0001F525>lung & cough gone. <U+0001F937>?||pfizer vaccine||Coughing, Cough, Hives, Numbness|
|Ivermectin was amazing when I got covid a mild sore throat for 3 days||ivermectin||Sore throat|
|Holy shit the pfizer vaccine got me feeling drunk! I just laughed my ass off for 5 minutes straight. It’s gonna be a long ass night. <U+0001F923><U+0001F923><U+0001F923><U+0001F926><U+0001F3FB><U+200D><U+2640><U+FE0F> #help||pfizer vaccine||Feeling drunk|
|Had COVID & had it bad. Real bad. Having said that I do not regret being vaxed. Got the monoclonal antibodies treatment during COVID & had side wicked effects for 2 months…hand tremors in right hand & heart palpitations.||monoclonal antibodies||Palpitations, Tremor|
|I used it when I had Covid unvaxd had a slight runny nose probs would have been the same without ivermectin bigggest scam||ivermectin||Runny nose|
|_hologram I had the Pfizer vaccine Mild fatigue and headache were pretty much par for the course.||pfizer vaccine||Fatigue, Headache|
|I am very sorry for the way you feel,it’s terrible. I also feel like the last 6 months were stolen from me as the first Pfizer vaccine ruined my life!I hope this nightmare leaves you and lets you live the life you always had 🙁||pfizer vaccine||Nightmare, Nightmares|
|What was really frustrating was I got the initial one shot Johnson and Johnson “vaccine”, had to wear a mask at work, and still ended up with the virus. I didn’t know I had it until I got tested at the doctor’s office during my physical because I had sinus infection symptoms.||johnson and johnson vaccine||Frustration, Infection, Sinus infection, Sinusitis|
|Well I got shingles 6 months after my second Pfizer vaccine shot.. And had a nagging head cold for about 2 months, and still caught the rona. So, take that for whatever it’s worth||pfizer vaccine||Coldness, Cold, Shingles|
|Ive had COVID 4 times. I got COVID before there was even a vaccine. What saved my life was Remdesivir. Just so you know, Im diabetic, a below the knee amputee and some other stuff Im working on to control||remdesivir||Diabetic, Diabetes|
|_dreams I took ivermectin, zinc, vitamin D, and vitamin C when I had Covid. Symptoms lasted 3 days, and fever broke after 24 hours of Ivermectin. Say whatever you want, it worked for me, and everyone around me. Zero complications. Even the old people were fine.||ivermectin||Fever|
This classifier was trained on a set of tweets manually reviewed and tagged. The classifier was trained using GloVe, a pretrained word embedding layer.
Webpage created in R version 4.1.0 (2021-05-18) and R Studio (Version 1.4.1717) using the following packages: plotly, kableExtra, formattable, treemap, and wordpressr.
- C. Sievert. Interactive Web-Based Data Visualization with R, plotly, and shiny. Chapman and Hall/CRC Florida, 2020.
- Hao Zhu (2021). kableExtra: Construct Complex Table with ‘kable’ and Pipe Syntax. R package version 1.3.4.
- Kun Ren and Kenton Russell (2021). formattable: Create ‘Formattable’ Data Structures. R package version 0.2.1.
- Martijn Tennekes (2021). treemap: Treemap Visualization. R package version 2.4-3.
- Simit Patel (2021). wordpressr: An API Wrapper for WordPress Site APIs. R package version 0.1.0.
- WHO COVID-19 Dashboard. Geneva: World Health Organization, 2020. Available online: https://covid19.who.int/ (last cited: Jun 09, 2022).
- Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.