Steemplus is a browser extension that adds plenty of features to your Steemit (mostly) , Busy and Utopian experience. You can find the complete list of features and installation procedure in our documentation.
New Feature : Steem Sincerity
Last week we came across @andybet's great initiative : Steem Sincerity Anti-Spam API and got in touch with him in order to make it even better.
The API classifies users in 3 different categories : Human, Bot and Spammers, based on a machine learning algorithm. While I perform quite well already, it was trained on a very small data set, which can cause some classification errors.
To overly simplify. the machine learning trains itself on a few accounts that have been manually attributed to one of these 3 categories. Based on similarities it will then attribute a likelyhood for other accounts to pertain to these categories. The biggest the training set, the higher the precision will be. That's where we need you!
Read on to see how all this has been implented into SteemPlus:
For every user you'll now have a label mentioning which 'category' of user it is:
This classification is available from within the posts, the comments, on the Trending etc. lists and the feed.
Here we can see that Steemplus is considered as a human. Great I've passed the Turing test ;p
But as I said earlier, it is not perfect yet and we can see some wrong category attributions:
For example, this user is considered at a bot although I know perfectly that he is human. Or did he fool me? In his case, the fact that he is a Utopian moderator make him post often the same kind of comments, hence the error.
Same for this one who's clearly supposed to be a spammer but considered as a human.
That's the reason why we need you feedback. To give it is very simple, simply click on the category attributed to open its popup. From there you can "vote" for the category that should be attributed. @andybets' algorithm will take this into account after filtering fraudulent votes, in order to enhance the classification algorithm. This means that you will not see the effect of your vote instantly.
A simple click on one of those button will let you give your feedback and help improve the machine learning algorithm.
This algorithm is based on what you post, what you like, what you comment on Steemit. Therefore some users, the new ones for example or the ones who are never posting won't be in any category.
The main difficulty we encountered was to attribute the category to everyone in the different Steemit pages. This took time since we had to scrap a lot of different classes. The button is available
On post's headers
For the Comments
On post footers
On the Blog
- On the Feed / Trending / Hot / ...
Please help us by giving feedback, together we can make Steem Sincerity API an awesome tool that will help filtering spammers and bots on demand. Do not hesitate to vote for the right category the user should be in, whether to correct the algorithm or show it that it was right.
We count on you!
Coming soon
- Offline mode : Currently to use Steemplus you need to be logged via SteemConnect, but we actually don't need to be connected for all the features.
Join us on Discord
Find @andybets announcement in here.
Big shoutout to @jerrybanfield and his budgets project that allow us the speed up the development of SteemPlus!
@stoodkev and @cedricguillas for @steem-plus
Powered by @adsactly
Powered by @utopian-io
Like what I do? Vote @stoodkev for witness!Posted on Utopian.io - Rewarding Open Source Contributors
For those who want to use it, Chrome extension link : https://chrome.google.com/webstore/detail/steemplus/mjbkjgcplmaneajhcbegoffkedeankaj?hl=en
As mentioned on the Github Repo Readme Page under Technical, you may also use this plugin with
Firefox
Opera
Please @stoodkev give this link under every Steemplus post. Would really make it easier. Thank you transisto. ^^
Thank you for the contribution. It has been approved.
You can contact us on Discord.
[utopian-moderator]
Hey @ms10398, I just gave you a tip for your hard work on moderation. Upvote this comment to support the utopian moderators and increase your future rewards!
Thank you for the contribution. It has been approved.
You can contact us on Discord.
[utopian-moderator]
Hey @vladimir-simovic, I just gave you a tip for your hard work on moderation. Upvote this comment to support the utopian moderators and increase your future rewards!
We need this tool because recenlty I have seen many spammers commenting on my post that don't have any relation with the article. We can see the real human who is reading your hard written blog. Great idea
I can't say it often enough that your extension is awesome. That's yet another feature that I'll really enjoy. I just want to say that if you implement offline mode you shouldn't let people vote if someone is a spammer/bot/human without being logged in.( Expecting that the login will still be required for some of the functions such as the voting slider)
Awesome! Already updated and love the classifier!
Thanks! For now it is not perfect yet, but with user feedbacks I believe Andy can make the API a real savior for the Steem ecosystem. Could be useful to know which users to blacklists for the bots for example.
Yeah I was already in discussion with him about how to best classify users and have a few ideas how to improve it.
Can you display maybe show it as a bar? Like how many percent are human. There is a difference between a 50% spammer and a 95% spammer.
Yea you can have this info by clicking the classification. We didnt display it directly because that would be too much info directly in the UI.
Can you make it a setting? I would definitely be interested in the additional data on first glance, not after a click
another major improvement, congratulation guys. awesome
You guys really need to fix the Spammer Tag. I'm sure it works sometimes as in the case of @sleezy.skeezey but my good friends and content creators @cryptotenx have been labelled as spammers when they only post original content that has been properly put together and they don't even post often. Please fix this.
Honestly, they should just put you in charge of all GUI designs for Steemit. Great new addition!!!
This is great news in finding spammers. Although it isn't perfect I can see it becoming more and more reliable in the future. upvoted
Made me LOL too. :-)
Hahaha! Kinda made me think of this...
Yup the irony. Kind of funny tho lol
I think this is a great update. I'll be sure to follow up and provide feedback. Is it useful to confirm correct classifications? Or only report the wrong ones?
Thanks! Both types of feedback will be appreciated =)
Cool tool. Just wondering if steemit is decentralized why can not people just go to add these features directly onto steemit? Like have a voting platform for upgrade enhancements on the platform and most votes gets installed. Just a computer novice here. Thanks.
love it love it love it
you have the #onelovedtube support, I push this application at a large number of people as its the easiest to manage your delegations along with so many needed features. I said "it has everything I wish steemit included from the get go" in one of my posts!
My first reaction was: Fantastic feature.
But then I'm going to visit my mother's blog and she appears as a spammer, she does not make many comments, I think her only sin has been to answer some bots thinking they are human.
I have reviewed the tag introduceyourself and there are several users who appear as spammers, checking their accounts there are some who even have only 1 comment in all their history.
I find it dangerous that this tool is implemented in steemplus when it is still so buggy. It could happen that by using this tool many users have a bad predisposition to new steemians. It is difficult to get to steemit and receive support, this can demotivate and further motivate the desertion.
Steem-plus is becoming one of the most important tools in Steemit, I promote it a lot in the Hispanic community. I think you should be more cautious with the implementation of new features. At least, for now, I think it should be disabled by default and to activate it should mention that it may have failures.
We will teach the bot to work better ;)
As I say in this post, the main goal of its early implementation is to get feedback to train the algorithm on a bigger training set. I thought I made it overly clear in this post. Maybe I can add a few caution words on the popup to remind that to users who may not have read this post.
Yes, please. It's very disconcerting to see the red label plastered all over my account.
I can't say I'm particularly pleased with being classified as a spammer. I've dedicated myself to recording excerpts from a great British philosopher on the blockchain with a daily post. It may not be content applicable to everyone, but it is precious to some.
As said in the post, the machine learning algorithm was trained a small set, the main purpose of showing this is to receive user feedback to make sure these kind of errors do not happen. I think I made it clear that for now the algorithm is far from perfect. @andybets is working on it though.
I read your full post on the imperfect nature of this application. You have my feedback now.
My opinion is that in its current state it is creating a whole new set of problems through trying to solve bot issues with a bot, while being a bot problem in its own right.
It is an interesting experiment, but it has serious implications for peoples accounts through false positives. It seems reckless and irresponsible on the part of the creators to use the steem blockchain population as guinea pigs in this experiment.
The Sincerity API currently thinks you are more 'Content Creator' than 'Spammer'.
Please see: http://steemreports.com/sincerity-accounts-info/?accounts=jamesallen
I'm trying to record the King James Bible on the blockchain. Your designation of this account as a spammer is not appreciated.
It is a labor of love. You may not appreciate it. You have a right to your opinion.
This particular move to automate the identification of 'spammers' is not winning me over as a convert to your project.
I went through the trouble to give cheetah and steemcleaners a heads up concerning my goals. Now I'm being undermined by automation.
This is not MY designation, it is a machine learning algorithm that needs to... learn. My post made that clear, by signaling to the API that you are indeed not a spammer, it will help it being smarter and make the right choices. I understand you wouldn't appreciate being called a spammer if you are not, but think about how important it is to have such a system for the future of Steem. Tell the system when it s wrong, make it grow!
I'd be more positive about it if you had put more forethought into how it should be implemented. By allowing the machine to display an assignation so prominently, you have essentially created a system whereby people are guilty until proven innocent.
Your philosophical outlook that the rights of the individual should be compromised for the good of the collective is in fact offensive to me.
Distancing yourself from the act of enabling the bot and the subsequent consequences of the bots actions does not disconnect you from responsibility either. I can roll a rock down a hill and the subsequent collisions could cause an avalanche of rocks. Am I free from blame? Or should I just blame it on physics?
Here is a suggestion, since I don't want to get bogged down in assignation of blame. Have the extension display a request that people rate the post, without displaying the assignation by default. Let people click on it to display your AI's guess. As it is only a guess. Over time it will be an educated guess, but for now it is not.
@stoodkev -
I fully agree with Blue here, I've seen some great Steempeeps being called bots and likewise spammers. I think it should be voted on by a human aspect whether or not an account should be considered for any of the three categories and then manually put into the system. I for one, have decided to pay no mind to this extension as it seems biased and overrated. The algorithm(s) being used were poorly coded as anyone that knows @seablue, knows without a doubt, he is no spammer. Does it check a profile's comments and replies? Or simply go by titles and frequency? Because that's what it appears to be doing to me. Yes, some of @seablue's titles are similar, but then by that logic, your extension bot would classify virtually every contest or motivational poster out there as a 'spammer'.
The Sincerity API currently thinks @seablue is more 'Content Creator' than 'Spammer'.
Please see: http://steemreports.com/sincerity-accounts-info/?accounts=seablue
The Sincerity API currently thinks you are more 'Content Creator' than 'Spammer'.
Please see: http://steemreports.com/sincerity-accounts-info/?accounts=kjv
Greetings. I do not know if I can say that I feel comfortable with the label given to me, since I do not consider my work and dedication worthy of this term, Spammer. I am a collaborator and I help many who strive on this platform, I hope there is some way to amend and verify this. Attentive to some answer.
Yeah, he should update this because I know your not a spammer. There's a loooooot of people who just were somehow labeled as a spammer, even though I know 100% they are not. Just laugh it up to a goofy mistake.
I appreciate the comment @truth-be-told and believe me, I would like to laugh at this and surely I will in some day ;)
See, he returned your humanity! LOL!!!
We know you aren't either sweets. This extension is not a viable option for people to really know a person or profile.
Thanks for the support @thealliance, it is very disappointing that they put a label on you and in no way give reason why you have deserved this denomination. It has definitely been a bitter drink for me.
This is great progress. Thanks for all you do. I'm happy to support stoodkev as witness.
this feature is awesome great work :)
I would love to see the classification in the votes too! :)
I am super glad to have found this post. I got on to Steemit through Steemplus and seen the new feature. I was excited to have spammers so easily detected! However, I was quickly disappointed to see so many people who work really hard on Steemit, labeled as a spammer. I am glad to see that this is the beginning stages because otherwise it could really ruin some people if someone were to judge them off of what Steemplus labels them as. I will be sure to provide feedback and do all that I can to ensure that this feature goes well because I think that this is a super good idea with so many people spamming these days.
This looks so good. Looking forward to the offline mode, since i do not know why you need access to accounts for the UI enhancement. But keep up the work, next step would be maybe to check for malicious links posted by the spammers
I'm classified as a Spammer. How do i get it changed to Human?
Another question, if my husband installed steemplus in chrome, would there be conflict if I install it in firefox? because I work in steemit for mozzilla and my husband for chrome. Would a conflict be generated on the pc or could it be installed on the 2 browsers?
I have steemit installed on two different browsers and haven't had any issues. I also have it installed on my phone and laptop, but then again I haven't used it very much and am just starting to make posts. Hope this helps you. Also I have liked and upvoted your post please do the same for my posts.
ok, gracias
GREAT NEWS
Well, why this miraculous machine signed me in spammers?
Because users don't understand ukrainian variation of cyrillic?
wow...this is really amazing....i guess it should also sort out votes in their percentage, to show the ones coming from bots, and humans.
I am a newcomer, it seems this app is interesting to try. success is always for you.
greetings from aceh, indonesia.@steem-plus
Thank steemplus. I use your extention for my chrome. It make me easy
amazing!already nice Ok
steemplus thanks! this is the most useful tool for Steemit! great thanks for updates!
very good news , but how do i update steemplus
which browser are you using?
firefox
i installed steemplus V 2.7.0.1
This one is 2.8
ok thanks il try and update it
Les gens accusent des comptes humains comme spammer ! Et il y en a beaucoup !
Ce sont pas les gens , c est le machine learning pour l instant, et les gens vont justement aider à corriger ca
Ok super ;-)
Salut , merci pour vos travaux, vous bonifiez mon steemit et j'adore !
Que la force soit avec vous ^^ maître jedi ! upvote for witness
without a doubt every day steemplus becomes the best application for steemit .. the most complete that there is. the only thing that is missing is to the mobile application of steemplus for what they can not use the application of your PC, You can use your cell phone or tablet
Surprised to see no spam on this post...lol Great job! Will start marking 'em :)
Awesome, it is great to see functionality added each time. Steemplus was already my favorite steemit add-on , and it only get tighter at first row . Great work, will it update automaticly with this new feature ? Thanks for the effort !!
This is brilliant
cool
Wow! First time I read about this project, and I think it's a great initiative, because it would help a lot to this community, especially in terms of spammers, they are usually annoying. much success in this project, really deserves all the support
Great work. I'll probably try this out now -- been wondering about what Steem-plus is all about.
If seen a lot of talk lately about trying to separate the trending page (or posts in generally) between "purchased votes" and "no votes purchased".
I think this would be a great feature to add to steem-plus as well (if it's not already in there). Would give people a heads up to see what is organic attention, and what is purchased attention.
Cheers.
I like the idea however I classified my other account (@MusicVoter) as a bot as I intuitively clicked the top button to get more information not realising that I was classifying it!
I think it needs to specify that clicking is a vote and maybe have an "are you sure you want to classify this account as XXXXX?" and/or have the ability to change your mind.
@MusicVoter falls into the class of account you mention above that uses the same comment. It is in fact a completely human account but I manually upvote qualifying posts then cut and paste the same comment.
Keep up the great work!
Add dsound tracks and DTube & YouTube videos, get more fans and earn $INDIE!
Follow @JuxtaMusic for More Of My Music
The last classification you make will be the one that is counted, so you can rectify your mistake.
Ah OK thanks. That wasn't obvious. Clicking all over the place to help! :-)
its kind of weird i saw my label as spammer :(
As said in the post, the machine learning algorithm was trained a small set, the main purpose of showing this is to receive user feedback to make sure these kind of errors do not happen. I think I made it clear that for now the algorithm is far from perfect.
Yups thank you :)
The Sincerity API currently thinks you are more 'Content Creator' than 'Spammer'.
Please see: http://steemreports.com/sincerity-accounts-info/?accounts=jikey
Thank you :)
I recently installed steemplus to do a delegation. It is a pretty impressive tool. I don't like to leave it running because it does slow down my Steem experience, but I use it about once a day.
This is great and I think we're all ready to do our part.
excellent feature! just turn the obvious even more clear!
Your Post Has Been Featured on @Resteemable!
Feature any Steemit post using resteemit.com!
How It Works:
1. Take Any Steemit URL
2. Erase
https://3. Type
reGet Featured Instantly & Featured Posts are voted every 2.4hrs
Join the Curation Team Here | Vote Resteemable for Witness
I'm not that impressed yet, but this is a nice step in the right direction. More than half of Steem development goes into exploiting the system. Thanks for joining the fight on the right side.
awesome! I am loving all these almost daily improvements and up dates!!! good stuff!!