The TweetWhisperer

Today is GDG DevFest 2019 in Trinidad. The organizers put out a call for sessions, and I was happy to share one of the ideas that had been rolling around in my head for a while.

I Facebook in pirate, don’t @ me.

So, here’s the TL;DR: my idea was to take my likes on @Twitter and funnel them into Google Keep. Along the way, I’ll automatically categorize the tweets and then confirm that categorization via a chatbot. Simple stuff.

So simple, I didn’t even use Visio to diagram it.

What I actually did:

Twitter Likes

I made an Azure Function that would periodically poll my twitter account and get the last tweets that I liked. To do this, I had to create a developer account in twitter to get the appropriate creds. The function was pretty simple:

Categorizing Likes

In the DotNetConf keynote a few weeks ago, I saw an ML.NET demo and I got the idea to use it here, too.

ML.Net to build models (easy peasy)

All my notes

I pulled all my notes in keep to train an ML model. It was very easy, particularly because I used gkeepapi, an unsupported library for interacting with keep.

Doing this made me glad that I could think in terms of a bunch of cooperating functions, because the function to extract the notes from keep was written in python, while most everything else is in C#.

KeepIt: A function to get my notes from Google Keep

The funny thing is, I didn’t really need the model. Most of the things I stored in keep, were in one or two categories – not very good for modelling. I guess I hadn’t really realized that. To be honest, I was probably storing things in keep that I had a very high priority on, which turned out to be mostly cloud things. Go figure.

How the bot will help change things

So, I’m grabbing my tweets, categorizing them based on history and preference and I’m ready to store them, except, as I’ve shown above, my categorization is whack. Thus, I also made a chatbot, that will take my liked tweets and ask me to adjust the category I’ve labelled it as.

TweetWhisperer: Helping me categorize my tweets better.

So, with these three components, a likes-harvester, a categorizer and a chatbot, maybe, I’ll get better at returning to these topics that I have an interest in.

Bots State

Ok, in 2016/2017 these were the bots I made:

Nurse Carter

Hansard Speaks

Time for Water

For some reason, I feel like there were more. Most likely, that’s because of perhaps just iterating on those above. I did make a few PoCs for work, like collaborating on the Teleios Code Jam one with our intern at the time, Joshua.

I also made a few ones we used for demos with clients, those put together things like QuikWorx, our low code solution creator at Teleios with SharePoint and Cortana.

This year, there are a few I’m going to go after in addition to iterating on the ones above. A friend of mine asked me to make a hybrid QnA CUI application. This tweet by Gary Pretty about a new way to sync QnAs might bring that back up.

My next new bot will be one that uses the Consumer Affairs Division data in some way. I hope to finish that over this long weekend in Trinidad.

One of the changes I’ve not been on top of have been to the Microsoft Bot Framework.  They’ve gone to General Availability and bots on the bot framework developer portal need to be moved over to the azure portal by March 31.  I’ll both move and update dependencies with the move to keep current with how to do things on the framework.

So, that’s it. I hope for more collaborations with the updates this year and perhaps more frequent updates.