Two years ago on a weekend, I built a tool to make it easier to evaluate Twitter accounts. Since then 36590 people used it to analyze 55390 different Twitter accounts.

Over the last months @mmkaradeniz and I made a new version. We launched it last night:

@mmkaradeniz @accountanalysis doesn't use machine learning or AI „magic“. Instead of telling users if an account is authentic or not, it helps them to evaluate the accounts themselves.

It visualizes the different features (date, time, type, app, etc.) of Tweets to make them interpretable. /1
@mmkaradeniz @accountanalysis The core concept is still the same, but it looks much better and is easier to operate. Not only for the users, but us developers as well. Enabling us to continuously roll out new features in the future.

Side-by-side screenshots of the old and new version. /2
@mmkaradeniz @accountanalysis Some people had questions what different charts displayed and how they could be interpreted. There are now explanations for all charts, that can be toggled on and off at any time. /3
@mmkaradeniz @accountanalysis The selected/retrieved Tweet count moved to the top to make it clear that not all Tweets of an account are analyzed. 3200 is the API limit by Twitter. It's possible to get more through the Premium API, but I don't think people would pay $100+ for the analysis of one account. /4
@mmkaradeniz @accountanalysis There is now an account card at the top of the analysis with basic info about the account. Mostly the same as you get when visiting a profile but with less clicks.

Additionally it shows the account ID. Useful when making screenshots and accounts change their screen name. /5
@mmkaradeniz @accountanalysis Next is the daily rhythm heatmap, the most loved feature of the tool. It aggregates the Tweets per hour per weekday to show daily patterns.

It gives a quick overview when an account is active and at the same time allows to drill deeper into the data. /6
@mmkaradeniz @accountanalysis Sometimes you are only interested in the Tweets of a specific time frame. The Tweetvolume by Date chart allows you to select the time you want to analyze and all other charts will only show that data. Very useful to understand spikes. /7
@mmkaradeniz @accountanalysis All charts are cross-filtered. By switching the selection between Twitter for Android and Twitter Web App, you can see how they supplement each other. My Tweets through a computer are more irregular with many volume spikes. Probably threads (see self-replies). /8
@mmkaradeniz @accountanalysis Hashtags and Hostnames help with understanding the primary topics of an account. If it is a single issue account or has a bigger variety.

It seems like I don't link out of Twitter often any more. /9
@mmkaradeniz @accountanalysis With whom does the account interact most often? Let's look into Replied Users, Retweeted Users and Quoted Users.

I love to reply to myself (threads!). But I also retweet myself often (Look at this awesome Tweet I made!). Finally, I mostly quote myself (Well.). /10
@mmkaradeniz @accountanalysis Finally, one of the biggest improvements over the old version: Most recent Tweets in the current selection. With the ability to load more (that wasn't possible in the past). Each Tweet has a type tag and a button to load the full Tweet.

Much easier to understand things. /11
@mmkaradeniz @accountanalysis Pro accounts existed in the old version, but they were neither advertised nor accessible. People had to send me a message to get price and payment details. After receiving the payment, I manually upgraded them in the database. Now it's self-service. /12
https://t.co/9CycLTc85m
@mmkaradeniz @accountanalysis To celebrate the launch of @accountanalysis on @ProductHunt, you can upgrade to Pro for 5,25€/month. (65% off). Coupon code in my comment: https://t.co/vKDtmqxAQ1

More from Tech

THREAD: How is it possible to train a well-performing, advanced Computer Vision model 𝗼𝗻 𝘁𝗵𝗲 𝗖𝗣𝗨? 🤔

At the heart of this lies the most important technique in modern deep learning - transfer learning.

Let's analyze how it


2/ For starters, let's look at what a neural network (NN for short) does.

An NN is like a stack of pancakes, with computation flowing up when we make predictions.

How does it all work?


3/ We show an image to our model.

An image is a collection of pixels. Each pixel is just a bunch of numbers describing its color.

Here is what it might look like for a black and white image


4/ The picture goes into the layer at the bottom.

Each layer performs computation on the image, transforming it and passing it upwards.


5/ By the time the image reaches the uppermost layer, it has been transformed to the point that it now consists of two numbers only.

The outputs of a layer are called activations, and the outputs of the last layer have a special meaning... they are the predictions!
Ok, I’ve told this story a few times, but maybe never here. Here we go. 🧵👇


I was about 6. I was in the car with my mother. We were driving a few hours from home to go to Orlando. My parents were letting me audition for a tv show. It would end up being my first job. I was very excited. But, in the meantime we drove and listened to Rush’s show.

There was some sort of trivia question they posed to the audience. I don’t remember what the riddle was, but I remember I knew the answer right away. It was phrased in this way that was somehow just simpler to see from a kid’s perspective. The answer was CAROUSEL. I was elated.

My mother was THRILLED. She insisted that we call Into the show using her “for emergencies only” giant cell phone. It was this phone:


I called in. The phone rang for a while, but someone answered. It was an impatient-sounding dude. The screener. I said I had the trivia answer. He wasn’t charmed, I could hear him rolling his eyes. He asked me what it was. I told him. “Please hold.”

You May Also Like

🌺कैसे बने गरुड़ भगवान विष्णु के वाहन और क्यों दो भागों में फटी होती है नागों की जिह्वा🌺

महर्षि कश्यप की तेरह पत्नियां थीं।लेकिन विनता व कद्रु नामक अपनी दो पत्नियों से उन्हे विशेष लगाव था।एक दिन महर्षि आनन्दभाव में बैठे थे कि तभी वे दोनों उनके समीप आकर उनके पैर दबाने लगी।


प्रसन्न होकर महर्षि कश्यप बोले,"मुझे तुम दोनों से विशेष लगाव है, इसलिए यदि तुम्हारी कोई विशेष इच्छा हो तो मुझे बताओ। मैं उसे अवश्य पूरा करूंगा ।"

कद्रू बोली,"स्वामी! मेरी इच्छा है कि मैं हज़ार पुत्रों की मां बनूंगी।"
विनता बोली,"स्वामी! मुझे केवल एक पुत्र की मां बनना है जो इतना बलवान हो की कद्रू के हज़ार पुत्रों पर भारी पड़े।"
महर्षि बोले,"शीघ्र ही मैं यज्ञ करूंगा और यज्ञ के उपरांत तुम दोनो की इच्छाएं अवश्य पूर्ण होंगी"।


महर्षि ने यज्ञ किया,विनता व कद्रू को आशीर्वाद देकर तपस्या करने चले गए। कुछ काल पश्चात कद्रू ने हज़ार अंडों से काले सर्पों को जन्म दिया व विनता ने एक अंडे से तेजस्वी बालक को जन्म दिया जिसका नाम गरूड़ रखा।जैसे जैसे समय बीता गरुड़ बलवान होता गया और कद्रू के पुत्रों पर भारी पड़ने लगा


परिणामस्वरूप दिन प्रतिदिन कद्रू व विनता के सम्बंधों में कटुता बढ़ती गयी।एकदिन जब दोनो भ्रमण कर रहीं थी तब कद्रू ने दूर खड़े सफेद घोड़े को देख कर कहा,"बता सकती हो विनता!दूर खड़ा वो घोड़ा किस रंग का है?"
विनता बोली,"सफेद रंग का"।
तो कद्रू बोली,"शर्त लगाती हो? इसकी पूँछ तो काली है"।
@franciscodeasis https://t.co/OuQaBRFPu7
Unfortunately the "This work includes the identification of viral sequences in bat samples, and has resulted in the isolation of three bat SARS-related coronaviruses that are now used as reagents to test therapeutics and vaccines." were BEFORE the


chimeric infectious clone grants were there.https://t.co/DAArwFkz6v is in 2017, Rs4231.
https://t.co/UgXygDjYbW is in 2016, RsSHC014 and RsWIV16.
https://t.co/krO69CsJ94 is in 2013, RsWIV1. notice that this is before the beginning of the project

starting in 2016. Also remember that they told about only 3 isolates/live viruses. RsSHC014 is a live infectious clone that is just as alive as those other "Isolates".

P.D. somehow is able to use funds that he have yet recieved yet, and send results and sequences from late 2019 back in time into 2015,2013 and 2016!

https://t.co/4wC7k1Lh54 Ref 3: Why ALL your pangolin samples were PCR negative? to avoid deep sequencing and accidentally reveal Paguma Larvata and Oryctolagus Cuniculus?