Net daily sentiment ranged from -24.7 for on Saturday the 13th to 34.99 for on Wednesday the 10th.
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
Anxiety was the most frequently observed medical condition mentioned. ADHD had the highest overall net sentiment of 19.04. Boil had the lowest net sentiment this week (-39.28).
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 108 tweets with an strong positive sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Anxiety, (2) ADHD, (3) Crying, (4) Pain, (5) Insomnia, (6) Nausea, (7) Stress, (8) Fall, (9) Sweating, (10) Vivid dreams. Of these terms, Nausea (n=6), Fall (n=5), Vivid dreams (n=4) were not in the top 10 most frequent terms across all tweets.
There were 164 tweets with an strong negative sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Anxiety, (2) Pain, (3) Crying, (4) Boil, (5) Coldness, Cold, (6) Forgetfulness, (7) ADHD, (8) Panic attacks, Panic attack, (9) Worry, (10) Numbness. Of these terms, Panic attacks, Panic attack (n=6), Worry (n=6), Numbness (n=5) 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 “sleep” within the search for “Tryptophan” had the highest overall weight. When the words are summed for each topic, Tryptophan 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 “pathway” within the search for “Tryptophan” had the highest overall weight. When the words are summed for each topic, “Tryptophan” 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|
|Woke up with my heart palpitating early in the morning because I missed my escitalopram intake last night. <U+0001F62E><U+200D><U+0001F4A8>||escitalopram||Palpitations|
|OK. 2nd day on the reduced dose of bupropion and maintaining dose of abilify. Brain feels good today. Allergies are kicking my ass, but my brain feels good. Lol
#depression #anxiety #flbghrhekejdhdggzysgshdjdjdbdjjjdjdhdhdhdhdujdkkdk #ugh
|Ps IBS ( feels like bad period pain). is caused by severe and ongoing anxiety. 2 years solid of it .. til I tried sertraline . No way in hell am I stopping it I could barely even eat before||sertraline||Anxiety, Pain, Period pains|
|it’s 4am I’m shaking as hell feeling nauseous and gagging @ the bathroom waiting for throwing up
this is the worst paroxetine withdrawal ever.
|paroxetine||Gagging, Nauseous, Shaking|
|anywayyyy my doc put me on trazodone for sleep and even though i went to bed at 2am i feel really well rested and i walked upstairs without any pain and come to think of it. i think this might just be my manic episode getting worse||trazodone||Manic, Pain|
|I’m fucking SOBBING on the inside omg I just finished Ozymandias… I cried for the first time in a month bc of my meds… this shit HURT my soul so bad it got me crying while on sertraline <U+0001F62D><U+0001F62D><U+0001F62D>||sertraline||Crying|
|__ I took bupropion for depression for about 7 months and it worked okay, but I did have some pretty bad side effects like extreme dryness, dry mouth and dry eyes being the worst, and hand tremors. Libido was great on it though, especially after years on prozac.||bupropion||Dry eyes, Dry mouth, Tremor|
|Oh damn <U+0001F62D><U+0001F62D><U+0001F62D> my issue is that I wake up every hour on the hour (without trazodone) and then if I dream it’s always nightmares that wake me up crying <U+0001F62D><U+0001F62D><U+0001F62D>||trazodone||Crying, Nightmare, Nightmares|
|Came off my Mirtazapine after being on it a year! My body isn’t coping… can’t sleep, insane night sweats when I do sleep and my stomach is in knots. Is this what withdrawal feels like??||mirtazapine||Night sweats, Sweating|
|GP switches her #antidepressant: “Shortly thereafter, I experienced major depersonalization & brain fog….I experienced some other obscure health symptoms (pressure in head, tinnitus, dizziness, fatigue, neck & head pain, etc). I saw many specialists….”||sertraline||Dizziness, Dizzy, Fatigue, Head pain, Pain, Tinnitus|
|z0”well slept good. thanks amitriptyline .. sorta a slow sluggish start for the morning.. but stress is way down and ping is up on my 2sq.. um good morning ric flair on my 2sq..”||amitriptyline||Sluggishness, Stress|
|my sertraline prescription is a week late, i’ve got biblical cramp AND i’ve been sent a fake dress off vinted. ALL BEFORE NOON. give me a break!||sertraline||Cramp|
|Day 1 of tapering off of duloxetine..
Really bad headache, feeling nauseous and dizzy
|duloxetine||Dizziness, Dizzy, Headache, Nauseous|
|oh wow, yeah i had like the exact opposite effect.
the weight gain is worth it, i gained from Bupropion.
Like night and day with these meds. <3
|literally bc of my paroxetine i cant take any cold/cough medicines for the sore throat n runny nose but advanced hydration grape pedialyte in those skinny bottles. is so fucking good. i was abt to chug the whole thing||paroxetine||Runny nose, Sore throat|
|four months into my tapering off journey with beloved #venlafaxine, i’m finally halfway through the hell hole. aside from a zapping brain, nausea and feelings of self-esteem in constant flux, it’s going great! no srsly, such withdrawal effects pale in comparison||venlafaxine||Nausea, Pale|
|forgot my pills yesterday and now withdrawal from venlafaxine hurtsssss im so dizzy and my brain is hurting||venlafaxine||Dizziness, Dizzy|
|I take trazodone every night, but lately my racing brain has basically been cancelling it out. I’ll fall asleep, but I’ll only sleep for a couple hours. Then I’m wide awake. It’s been fucking with my work, too. I’ll forget what I’m doing in the middle of doing it.||trazodone||Fall, Forgetfulness|
|_cryptonat I took some amitriptyline’s and relaxed but now back to the crypto and still in pain so ill take your <U+2764><U+FE0F><U+2764><U+FE0F> to see me through the rest of the day. Thank you so much – so sweet of you.<U+0001F60B><U+0001F618>||amitriptyline||Pain|
|I had to have 6 months of therapy and Sertraline before I could be referred for an MRI because a GP and physio were insistent my neck pain was caused by stress and unresolved trauma… I had bone spurs (and severe bruxism).||sertraline||Neck pain, Pain, Stress|
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.
- 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.