Anti-Depressants Twitter Report for the week of June 12, 2022

Daily sentiment

Net daily sentiment ranged from -20.37 for on Sunday the 12th to 27.45 for on Thursday the 16th.

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

Pain was the most frequently observed medical condition mentioned. ADHD had the highest overall net sentiment of 27.66. Crying had the lowest net sentiment this week (-46.67).

medical conditioncountsentiment
Coldness, Cold14-7.33

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

Positive tweets:

There were 114 tweets with an strong positive sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Anxiety, (2) Pain, (3) Insomnia, (4) Sickness, (5) ADHD, (6) Redness, (7) Inflammation, (8) Sweating, (9) Coldness, Cold, (10) Fall. Of these terms, Redness (n=5), Inflammation (n=4), Fall (n=3) were not in the top 10 most frequent terms across all tweets.

Negative tweets:

There were 175 tweets with an strong negative sentiment. The top 10 most frequent medical conditions mentioned within these tweets were (1) Pain, (2) Anxiety, (3) Crying, (4) Fatigue, (5) Sickness, (6) Boil, (7) Forgetfulness, (8) Worry, (9) Coldness, Cold, (10) Fear. Of these terms, Fatigue (n=8), Boil (n=6), Fear (n=4) were not in the top 10 most frequent terms across all tweets.

Word-level analysis

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 “day” within the search for “Bupropion” had the highest overall weight. When the words are summed for each topic, Sertraline 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 “depress” within the search for “Sertraline” had the highest overall weight. When the words are summed for each topic, “Bupropion” 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)

tweetsearch topic(s)medical condition(s) mentioned
yeah, i used to sleep for most of the day and at night, but now i just sleep at night (since i stopped taking sertraline and started taking my lurasidone at night). i’m so fatigued though =( sighsertralineFatigue
Hi! I‘m on 2×25 Nortriptyline/ day for chronic headaches. For migraines, I‘m taking 2,5 mg Zolmitriptan (along with meds for stomach/better intake). Had to experiment before doc and I found the right med – amitriptyline for example made me tired 24/7.amitriptylineHeadache, Migraine
Depends on the meds. I take Trazodone to sleep and I started getting tremors. I’m weaning myself off it now.trazodoneTremor
From my experience the side effects fade within fits 2-3 weeks. My first 3 weeks on sertraline I slept 90% of every day, had tummy upset most days and just felt shut down, but then a fog lifted, got my appetite back etc etc and no only side effect I have is a slight hand tremorsertralineTremor
That reminds me, when I went up on trazodone awhile back, I got night hallucinations then too. Mine only happened when my eyes were closed, or it was very dark. It was like dreaming while awake. It sucked bc it was the only thing that helped me sleep at the time.trazodoneHallucinating, Hallucinations
I stopped taking sertraline abt 2 weeks ago bc it was giving me consistent nausea and joint pain in my ankles, and since then all my dreams have been extremely scary and bloody <U+0001F635><U+200D><U+0001F4AB>sertralineJoint pain, Nausea, Pain
I feel for you. When I was on IV chemo I had horrible bone and joint pain. My oncologist prescribed Duloxetine. It took a week to get in my system. Game changer for me. I was able to relax and not have the horrible aches.duloxetineAche, Joint pain, Pain
I’ve had 3 fluoxetine anti depressant tablets that’s 60mg I feel so happy lol. I still have pain from the shingles but it’s getting better I’m now out of bed and lay on the settee now so that’s a start I’m going back to work on SaturdayfluoxetinePain, Shingles
I was on propanolol and sertraline. The propanolol worked quite well for me with my anxiety but would leave me feeling a bit crap. Sertraline were the devil’s meds though I’m suresertralineAnxiety
ive slept like 3 hours in the last 48+ 🙁 i wake up anytime i finally fall asleep then can’t fall back asleep. i still have some trazodone left but i h8 taking ittrazodoneFall
i’ve been up since 6:30 but trazodone gives me such a bad “hangover” feeling in the morningtrazodoneHangover
Venlafaxine day 5, I’m feeling ok. Tired and a little dizzy, but ok. No major side effects.venlafaxineDizziness, Dizzy
I was on Wellbutrin for a few years. My diagnosis was anxiety and other meds made me gain weight (which was/is what causes me anxiety). I’ve been on Amitriptyline for many years because of my IC. I’m happy to answer questions.amitriptylineAnxiety
i tried duloxetine for joint pain from hypermobility, n only had a little bit of pain relief, tho idk how that compares to fibromyalgia also i ended up developing tics when my doctor took me off of it cold turkey lolduloxetineColdness, Cold, Fibromyalgia, Joint pain, Pain, Tic
TW – self-harm mentioned Nothing has brought me joy in the recent years other than this boy and my then boyfriend, but after almost two solid years of being off meds, I am now back on Venlafaxine. The past few months have been hard and I have been getting negative thoughts 1/?venlafaxineNegative thoughts
Hello, I’m still suffering from Venlafaxine withdrawal and while it sucks and I’ve slept for far too long today… fuck I’m so tired… I’ve come up with a new project to work on when my brain doesn’t feel like it’s going to melt through my ears. (I’m being dramatic don’t worry).venlafaxineWorry
I am deeply depressed today but my good girl sertraline doing the most to tell me I’m fine whilst giving me all the pain of being depressed<U+0001F60D>sertralinePain
When I took Lexapro to treat generalized anxiety disorder, I had such a violent adverse reaction to it. Severe foggy-brained headaches, inability to sleep, my feet itched like a fire-ant attack, etc. Didn’t take the pill one day &amp; felt fine so the doc switched me to Sertraline.sertralineAnxiety, Headache, Itching, Violent
I love doxepin. I take 6 mg for PTSD insomnia (waking at 2 w/panic attacks). No big side effects except I was a bit groggy the first week, probably from restoring sleep debt.doxepinGroggy, Insomnia

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.