Accountanalysis

A tool to evaluate Twitter accounts

2 followers

A tool to evaluate Twitter accounts

2 followers

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.

Launch tags:Social Media•Analytics•Marketing

Launch Team

Atlassian LoomShow, don't just tell with Loom

Promoted

findable 2.0

Hunter

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?

Report

7yr ago

Accountanalysis

Maker

@__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/...

Report

7yr ago

Kudos for the launch of this grat application. Is it possible to implement e.g. AI Technologies like IBM's WATSON in tools like accountanalysis?

Report

7yr ago

Accountanalysis

Maker

@bavaturka Thanks! We decided to not use AI to make the analysis more transparent and comprehensible. There are other tools like botometer, botrnot and similar ones which focus on bot detection through machine learning. While they are nice to calculate scores on big numbers of accounts, they are inaccurate when looking at single accounts. Some researchers use such fully automated tools to get a list of suspicious accounts and then inspect those accounts with accountanalysis.

Report

7yr ago

Bardeen

This is really cool. What kind of insights do you find the most useful? Also, how was the Twitter API to work with?

Report

7yr ago

Accountanalysis

Maker

@tim_nugmanov Thanks! It depends on what I am trying to find out. Overall I look at the daily pattern the most. It allows me to spot most highly automated accounts with a single glance. The not so obvious but most powerful feature is the crossfiltering. By filtering for specific time frames I can make things visible I wouldn't catch otherwise. Especially for semi automated accounts I can often filter out the noise be unselcting certain sources and once again make the relevant patterns visible. I like the Twitter API. For me it nearly always worked. The removal of the features didn't affect me because as I wasn't building a regular client. I'm still aware of the risk that Twitter could change their API at any time. Lately they put in effort to work closely with devs and researchers to add endpoints we need. I am looking forward to playing with the new Twitter Labs API and maybe integrate some of it as experimental features. Especially the added metrics could be useful. For other projects I used the Premium API as well, which I love but is simply to expensive for most projects. But I already have a plan how to integrate it. Not sure if people would pay $100 upwards for a single analysis.

Report

7yr ago

Accountanalysis

Maker

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.

Report

7yr ago

Accountanalysis

Maker

@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.

Report

7yr ago

Product Hunt

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.

Report

7yr ago

Accountanalysis

Maker

@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.

Report

7yr ago

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

Report

7yr ago

Accountanalysis

Maker

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.

Report

7yr ago

Bardeen

Gotcha! I wonder how this could be useful for entrepreneurs to increase engagement with their audience

Report

7yr ago

Accountanalysis

Maker

@tim_nugmanov If there are accounts that I admire and want to copy, I would look at their behaviour with the tool. How active are they? When? How often do they Tweet? What kind of Tweets? What URLs? Then I would look at my own account and reflect on how I should change my own behaviour. If there are accounts I would like to engage with (investors?), accountanalysis could be used to see when they are online and who the retweet most often. Sometimes it's easier to be noticed by the people who they already pay attention to. The tool would show which websites they share most often as well.

Report

7yr ago

1 2

Reviews