Proposing *TrufflePig*: An Artificial Intelligence to help Minnows and Content Curators

It is hard to keep up with all Steemit Posts!

Steemit can be a tough place for minnows, as new users are often called. I had to learn this myself. Due to the incredible amount of new posts that are published by the minute, it is incredibly hard to stand out from the crowd. Often even nice, well-researched, and well-crafted posts of minnows get buried in the noise because they do not benefit from a lot of influential followers that could upvote their quality posts. Hence, their contributions are getting lost long before one or the other whale could notice them and turn them into trending topics.

However, this user based curation also has its merits, of course. You can become fortunate and your nice posts get traction and the recognition they deserve. Maybe we can find a way to support the Steemit content curators such that high quality content does not go unnoticed anymore. I have a proposition to do exactly this with the help of Artificial Intelligence and Machine Learning. I propose TrufflePig a new bot that digs for hidden Steemit gems (or truffles if you like) that were overlooked by the curation crowd.

Caution future versions of TrufflePig may diverge from depiction ;-)

Let Machine Learning Help the Steemit Community

I am a Data Scientist and do Machine Learning for a living. I also have experience with using Artificial Intelligence to analyse written texts and documents.

The basic idea is to use well paid posts of the past as training examples to teach an Artificial Intelligence (AI) how high quality Steemit content looks like. In turn, the trained AI can be used to identify posts of high quality that were missed by the curation community and did receive much less payment than they deserved. I have the following plan for the TrufflePig bot:

• The bot will be regularly trained on new Steemit posts to identify currently trending topics.

• It will also vote on overlooked and undervalued posts (so you may delegate Steem Power to it if you like to support minnows).

• In addition, it will publish a list of the top undervalued contributions once or twice a week and direct attention to these contributions. Payouts of these top-posts may cover the server costs.

• Later in the future, there will be an API and/or website available where you can post your own texts before publishing to get an estimate of their value.

You haven't heard the best part of this proposal, yet. This is not just a vague idea, but I already experimented a bit and the results look promising! I have coded a prototype to showcase that a bot can be used to help with curation on Steemit. YOU CAN FIND THE PROTOTYPE HERE. However, so far the prototype is an offline version and rather a proof of concept. I still need to create a well tested code project, setup a proper bot that runs on a dedicated server, and maybe even establish a full Steemit node to allow better data crunching for the training of the Machine Learning method.

So what can you do? You can help me by upvoting and resteeming this post as well as my other post about the prototype coming tomorrow. The payout will help to cover initial development as well as server costs. The project itself will be open sourced and published on my Github account. However, I won't make any promises, yet, about the associated license (i.e. MIT versus rights reserved). Furthermore, I have to see whether it make sense to develop under the patronage of utopian.

I will come up with a proper roadmap in a couple of days, and, of course, will keep blogging about the development of the bot. So stay tuned! Leave your feedback and suggestion in the comments. And don't forget to checkout the prototype of TrufflePig HERE!