Comment by caseysoftware | Hacker News Reader

Comment by caseysoftware | Hacker News Reader

Previously, as a developer evangelist with Twilio, I had to know the tech events and tech leaders in my local community. While I didn't figure out a repeatable approach then, in late 2015, it hit me.

I built a bot network that reads tech events - mostly meetups, some conferences and workshops - for a given city from a variety of sources and tweets them. I use machine learning to determine hashtags, time of day to tweet, and new data sources. When I launched Austin - https://twitter.com/ATXTechEvents - in September 2015, I got 900 followers the first month. I suspected it was a fluke so launched Dallas FW and Houston to test. It wasn't a fluke.

In 2016, I've launched 45 different cities in the US and the network has 100k followers collectively, has its own automated weekly mailing list, and is generating 1.4M+ impressions/month. Revenue is affiliate fees for conferences (we are a media partner for O'Reilly) and workshops and selling the ad blocks in the newsletter. Almost all of that is automated. The revenue is pretty minor right now but growing and I spend 1-2 hours on it a week.

The landing page is here: https://techeventsnetwork.com/ (only some of the cities) and the full list of cities is here: https://twitter.com/TechEventsNet/following

Btw, by plugging into meetups first, I found a super receptive audience. After a decade+ of planning UGs, I knew the most important but easily forgotten step is promoting the group.

The Tech Events Network tweets most groups either the morning of or night before and five days in advance, so you have a couple chances to notice. Further, occasionally it mentions the meetup group's twitter handle so easy RTing.

(All automated and sometimes I'm surprised about what it's found.)

> I use machine learning to determine hashtags, time of day to tweet, and new data sources.

can you elaborate more this?

Sure.

My last startup - Clarify.io - did automatic speech recognition through machine learning. Since I was doing the roadmap and API design, I wanted a better understanding of ML and started digging into it.

For context, I started by studying the Austin tech community since that's what I know and could manually check the conclusions.

The basics:

Overall, the system tracks 5500+ groups, conferences, etc which is close to 60k events. It grows as it discovers new groups and events via a few channels.

As it finds and imports groups and then events, it categorizes each based on how they're described. If it's from Meetup.com, the category data and topic are reasonably good so it starts with that. If the source is Eventbrite, less so. If the source is an event website, even harder.

After ~15 months, it's discovered about 105k keywords/phrases, some only barely related. Of those, only about 7500 are actually useful. Not surprisingly, they include languages, frameworks, companies, products and combinations of words. (Side note: I've found words like "hacking" are less of an indicator now than when I started.. because everyone is "hacking" something.. marketing, cooking, etc.)

From all that, groups are qualified in/out based on their overall score. I manually review things that are borderline but that's 2-3 most weeks. That keyword/phrase list also feeds into the hashtags that get used.

The first version of this - hardcoded, no ML - was hacked together in a day. I've rebuilt it from the ground up to wire in the ML processing to scale across all the cities.

I later did some major refactoring to have pluggable output so it can broadcast into a Slack channel (done & released) and eventually send you a reminder DM or text (via Twilio!)

Oh, and I'm careful to disqualify job fairs. You might find a session about resume writing or "getting a better job in tech" but not the fair itself. I've gotten a bunch of thank you notes and tweets about that aspect.

They have their place, just not in my system.

Solid idea! I think this will be supporting you in a year and will be killing it in five. Quite impressive.

I'm based out of Baltimore and I follow your Baltimore Twitter bot. If you need any help or Quality Control for Baltimore events let me know!

Well played sir. And thank you.

Reply on news.ycombinator.com