Underrated - Yet another list on Steemit
Let's accept the fact that NOT quality determines the payout of a post on steem blockchain. Its the amount of attention you get for your post that will be as important as the quality. In fact, it is not just attention. It is the attention of the stakeholders of steem that you need to find to get a share.
Today attention is by far mostly distributed by the Steemit.com Frontpage. I read statistics where it is about 90% that comes from SteemIt.com . Especially if you don't bring in a ton of followers from other social media sites, this is your primary source of readers.
How to get attention for your quality post?
Well, you can buy it by sending money to many of the upvote & resteem bots that are out there. You can buy your way on the front page with the promote feature on steemit.com.
You might find a manual curator that looks for quality content. There are many of those fellow steamians out there that work hard on finding new good content for curation manually. But also their attention is limited.
Would there be better ways to distribute attention to quality posts?
I propose to introduce a new list "Underrated" on SteemIt.com.
Four out of the five lists on the Steemit Front Page (Your feed, trending, new hot and promoted) you either have to have already the attention or you need to have money to get it.
Underrated should focus on listing quality content that matters to the reader. It's a personal list that is tailored to the reader's interest and his understanding of quality.
How can we accomplish this?
The Machine learning field provides for this kind of topic a particular useful algorithm that is called "Recommender System."
It will use your votes on other posts in the past to find similar posts that have been created.
As everyone has a different understanding of quality, it will match the quality you have voted before. But also text understanding & keywords will be used to measure the similarity of the topics you already voted.
The required type of Recommender System is called Item Based Recommender System (https://en.wikipedia.org/wiki/Item-item_collaborative_filtering). It's been invented by Amazon and used for similarity between products that Amazon wants to recommend.
What should not be on this list?
It should not only recognize the similarity between posts. The algorithm should also consider the chances these posts will lack attention.
Therefore additional selection criteria should be considered.
- Current value
- Avg. Payout of posts from the author.
- Time of posting (only consider day 1-7)
We could again use an AI algorithm that predicts the payout of a post. If this is below a specific margin, the post qualifies for this list.
Underrated should focus on new posts that are unlikely to get the attention themselves.
Underrated should not display a post anymore when it got a share of attention and reached a certain amount of votes/value.
What problems would be solved?
- Distribute the attention to new steemians will help steemit to grow faster.
- It will help quality authors to develop quicker and stay on the platform
- It will give all of your votes additional value because it improves your own user experience.
- It makes it easier for niche content to get visibility for their particular audience.
- It will make bot votes less attractive if they don't target your interests
- It will help curators find quality authors they can invest.
Dr. Make
Open Source Contribution posted via Utopian.io
I like the idea of an "Under-rated" tab. Though there's a bit of a mix about what would qualify for this. If we personalised it; things you might like that are probably underrated, then it could work very well.
However, if the metrics are too crude then the metrics can be gamed. Particularly if the metrics are site-wide and not personalised. For example, I can have a minnowbot army upvote to subvert any upvotes / payout metrics.
I think we have a slight disagreement in quality - but I think the difference is semantic so I'll leave it at that.
Quality is what you vote on only your own votes count. And then we measure the distance between new posts and those that you already voted. This list should be personalized as much as possible in both dimensions quality and topic.
Define distance and how you might measure that. That's the little important detail.
Lexical measures of distance are not a reliable substitute for semantic distance - and we'll need semantic distance for determine topics. And, quality, well, I'd argue that quality is a level of difficulty again above semantic distance.
Don't take this to mean I don't think your idea isn't sound - but we shouldn't over expect it'll deliver perfect results. Probably good enough results though.
I plan to publish some experiments about it. Already started with the extraction of data. For semantic distance, I want to play with gemsim and test doc2vec, word2vec or just tf-idf. For quality maybe similar measures like the utopian.io bot can be useful. A bunch of KPIs that might assemble loosely quality and then the distance between those I voted before and he new ones to identify the personal quality. Personal quality should easier to find then absolute.
You seem to know what you're doing. I think you'll be quite successful actually.
Thank you for the contribution. It has been approved.
You can contact us on Discord.
[utopian-moderator]
Hey @drmake I am @utopian-io. I have just super-voted you at 56% Power!
Suggestions https://utopian.io/rules
-Utopian has detected 2 bot votes. I am the only bot you should love!!
Achievements
-Good amount of information. Thank you!
-A very informative contribution. Good job!
-Votes on this contribution are going well. Nice!
-You have less than 250 followers. Just gave you a gift ;)
-You are generating more rewards than average for this category. Super!
-This is your first accepted contribution here in Utopian. Welcome!
-You have just unlocked 6 achievements. Yeah!
Up-vote this comment to grow my power and help Open Source contributions like this one.
img credz: pixabay.com
Nice, you got a 4.0% @minnowbooster upgoat, thanks to @drmake
Want a boost? Minnowbooster's got your back!
The @OriginalWorks bot has determined this post by @drmake to be original material and upvoted(1.5%) it!
To call @OriginalWorks, simply reply to any post with @originalworks or !originalworks in your message!
Congratulations @drmake! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOPCongratulations @drmake! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOPCongratulations @drmake! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOPGreat information, thanks for sharing @drmake!
Congratulations @drmake! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOPCongratulations @drmake! You have completed some achievement on Steemit and have been rewarded with new badge(s) :
Click on any badge to view your own Board of Honor on SteemitBoard.
For more information about SteemitBoard, click here
If you no longer want to receive notifications, reply to this comment with the word
STOP