Accountanalysis

A tool to evaluate Twitter accounts

#3 Product of the DayAugust 31, 2019
With accountanalysis you can evaluate Twitter accounts faster. Reasearchers and journalists use it determine how automated and fitting an accounts behaviour is, when it's active, which apps it uses and what URLs it shares.
Discussion
Would you recommend this product?
4 Reviews5.0/5
Hello Producthunt! I am a Social Media Analyst who helps journalist and the public to understand various social media phenomenons. My background is in social science and humanities. Two years ago I got many questions about bots and inauthentic accounts. I argued that tools that are based on machine learning work great for classifying things that don't change much, but inauthentic behaviour evolves constantly. At the same time it's obvious that computers are better at certain tasks, like collecting data and calculating statistics. One weekend in autumn, I coded a prototype to show how computers can visualize Tweets in a way that makes it much faster for humans to interpret them. Since then over 30k people used the tool to analyze Twitter accounts. Over the last view months @mmkaradeniz helped me to rebuild it from scratch. It's now shinier than ever and way more user friendly. I am excited that I can finally show the new version to everyone. If you want to test the Pro version with more Tweets per analysis and less clicking, use the coupon code "PRODUCTHUNT" to get 65% off for the first 3 months. I am looking forward to your questions and feedback.
@mmkaradeniz @luca Got some pretty cool insights using this! Any way for your to have 'action suggestions' box for making all the data actionable? Eg: "This user's 'Daily Rhythm' pattern suggests that you are most likely to get a reply from them if you engaged on Thursdays between 3pm and 6pm." OR "This user does not like to be disturbed on Sunday mornings". Some other UIUX related pointers - https://app.usebubbles.com/7844f...
@kanad_bahalkar It makes me happy that accountanalysis is useful to you. At the moment the tool is used by very different groups (researchers/journalists and marketers) which would mean that such suggestions need to be customized for each group. I can imagine it as an option in the account settings. "I am a marketeer" / " I am a researcher". And depending on what someone choose, we show additional info. "Most Tweets come from automation tools.", "Account seems has no awake/sleep pattern", "Most active in the morning". We have to figure out, if we should re-calculate those things depending on how users filter Tweets or not. Quite a big feature. Until I am able to determine it's impact, it has a low priority. - Tooltip for "selected/retrieved Tweets" is already in work. "Retrieved" tells you how many Tweets there are in total in the current analysis. "Selected" refers to the number of Tweets that are currently filtered. You can click on any feature (hour of weekday, time frame, Tweet type, replied to account) to filter for those Tweets. And combine filters from all charts. "Selected" will always tell you how many Tweets pass those filters. - Daily rhythm. Google maps only shows 6am to 2am of a single day at a time. accountanalysis shows all 24 hours of 7 days at a time, because we are more interested in general patterns than in current volume. The daily rhythm of @producthunt becomes easier to read, once you exclude buffer, because it posts once per hour 24/7. - The search box is important, but isn't used as much as the crossfiltering. It's not like an search engine where you run several searches after each other. It's more like opening a file and then working with that file for longer. - Most people don't need the explanations, but it makes it easier for new users to get started.
First of all kudos @ launch You have a lot of experience in analyzing networks of twitter accounts (e.g. to identify bot nets). Can you elaborate how this is done and maybe whether accountanalysis can help with it?
@__tosh Thanks for hunting accountanalysis! Identification of groups of bots starts with single accounts in most cases. Sometimes when looking at a trending topic there a weird Tweets or an account is suddenly followed by several similar looking accounts. Once you have the first suspicion, you investigate. Just visiting the profile of the account can be enough. If your suspicion grows, you can run the account through accountanalysis. The vast majority of bots isn't very sophisticated and the daily activity pattern already shows that the account is active 24/7. But even if that's not the case, you can look at the other features of the account. Bots often tweet in many languages and about things that have nothing to do with each other. In accountanalysis you would look at the language and URL graph. Once you are certain that it is a bot, you can try to find accounts that are operated by the same entity. Again, you look for patterns that are specific for that group. Maybe the interface (app aka source) they use or they all share a specific link or use a weird typo. With that information you go back to the Twitter search to find more accounts like them. Once again, running them through accountanalysis allows you to see similarities. Once you found a pattern that has few false positives, you would need a tool that allows you to gather many accounts at once and test them for patterns. I wrote a Python script for that (twecoll3) and use Gephi to create a network visualizations of the whole network of bots. Hopefully it will be possible to do that directly in accountanalysis one day. If anyone is interested in such stuff, I post bot hunting threads on Twitter from time to time. - Network of accounts, operated by humans, that engage in inauthentic behaviour that can be identified through special hashtags: https://twitter.com/luca/status/... - Bots that were active before the national election in Germany: https://twitter.com/luca/status/... - Network of Reply spam bots, identifiable by their typos: https://twitter.com/luca/status/...
It's not surprising but looks like over 70% of my tweets are replies to other people. Interesting see some of these results though. P.S. Recently @shl told me about Social Blade, another useful social analytics tool for those interested. P.P.S. @aaronykng, check this out.
@rrhoover Thanks for taking a look. Amount of replies are often a good indicator how approachable someone is on Twitter. But sometimes it just means they love to use it as a chat. Can be checked by looking if they are very talkative to a few accounts. You actually interact with a big number of users. Best time to get a reply by you is in the morning when you are generally most active on Twitter. Not on Saturday though and your Sunday Twitter starts two hours later. Socialblade is great because it has historic follower counts. Something that is normally only accessible by the account owner in their Twitter Analytics Dashboard. And only on a per month basis. Downside is that Socialblade can only track accounts it knows. Especially smaller accounts often have no history there.
Looks really interesting! Gonna try it out!
@alex_chernikov Thanks. Let me know what you like most.
Impresses with the ease to reveal patterns in twitter accounts. Not only great for analysing bots, but also a great tool for high level monitoring of corporate accounts. Great Work @luca and @mmkaradeniz
Thanks @bernd_paulus. Absolutely. I love to look into which tools different corporate accounts use and how often. Product Hunter (https://accountanalysis.app/twit...) for example uses Buffer a lot and consistently. 1 Tweet per hour 24/7. Reasonable with a global community. In the morning of weekdays frequency is increased to 2 Tweets per hour. Manual Tweets (Twitter Web App and iPhone) are much more infrequent with some spikes like 80ï Tweets on International Cat Day.