Everything I've learned in 3 months on TikTok

So I'm not new to social media, but I put off starting a TikTok for a long time because I just couldn't handle the idea of another platform to maintain. I already have a LinkedIn (with articles like this one!), a fashion Instagram (a souvenir from my past life as an international model), a Twitter and a Dev.to for my tech writing. However, I finally bit the bullet at the end of October and started a TikTok, and I have learnt so much along the way! In this article I'll outline everything I learnt the hard way about the platform, and all of the benefits I hadn't considered before making my account.

I can already hear you groaning about TikTok - I used to think it was just a dancing app for kids too!

I challenge you to put your existing reservations aside just for this article, as I really think there are huge gains to be made via this platform for the overarching tech landscape and community.

1. Growth is hard, but just push through

There's no shortage of experts making videos about how to grow your account to XYZ followers in XYZ days and it's important to remind yourself that if all of their tips worked, none of these accounts would exist. Everyone is trying to figure things out at the same time, and some advice is great but other advice is complete garbage - instead of trying to find magic beans just find a consistent cadence to upload that works for you, and figure the rest out as you go along.

Here's my last 60 days worth of analytics - note that things really fluctuate depending on if I uploaded anything, and if it caught on:

On the other hand, this is my cumulative follower count:

Things are pretty stagnant at the start because I ended up taking 10 days break, but then things really picked up in the holidays when I had more time (and mental energy!) to post.

After consistent posting, TikTok isn't the largest platform I have (yet!) but it is my fastest growing.

2. So many users want to transition to tech careers

This is by far the biggest realisation I had - the user base is fundamentally different to all of my other networks, and there are thousands of young people wanting to explore tech careers, as well as established professionals who want to transition to a tech career.

I think this builds on the narratives around 'The Great Resignation' or as Kara Swisher puts it - 'The Great Reassessment'. So many people have seen glimpses of tech careers, either through 'Women in STEM' movements or just more transparency around the people behind the tech platforms they use on a daily basis, but they still have absolutely no idea what sorts of jobs are available in tech. There's a fantastic community of creators who are pulling back the curtain on what it's like to work and flourish in tech careers, and there's so many interested viewers!

I'm yet to see organisations really make the most of this at scale - there's lots of brands using TikTok for B2C marketing (Duolingo is my absolute favourite example of this - it's absolutely unhinged and chaotic which is perfect) but there's not a united push by large organisations to use the platform for employer branding/recruitment/upskilling of the incoming talent pipeline. This is a huge opportunity, which would benefit the industry at large.

3. Don't put effort into content

The message is so much more important than the method! There's always a lot of talk about what "the algorithm" prefers but at the end of the day, humans are human! Relatable stories, or easy-to-digest messages will always do better than well-produced nonsense. Just as there are so many business books that should have just been a blog post, there are many blog posts/ebooks that would have much higher engagement and recall if they were distilled down to something short and memorable.

You don't need Final Cut Pro/Premiere Pro, you can edit as you go in the app and it's faster than you think.

4. The videos you don't like will end up doing the best

Similar to point 3 - there are so many videos I put effort into that I was proud of and just didn't end up doing well at all. Big examples of this are my first two videos - this one about AWS Snowball and this one about Amazon SageMaker. They're absolute nonsense (no one will dress up as SageMaker for halloween) but I made these before I worked out how to use the TikTok native editor so they took so long to make and they didn't get any traction! Another example is this one-take-wonder of me reciting Julia Gillard's misogyny speech. I love this video but it didn't really catch on - perhaps my viewership is too young to remember this!

On the other hand- the videos I absolutely hate are my best performing videos. Eg this one which has 44100+ views and this one which has 27500+ views. These were my laziest ideas and I put zero thought or energy into them, but they did really well.

With that being said - videos "doing well" is not the end game! Getting to the fyp (the 'home' screen with lots of videos) for other users is great to reach new audiences, but there's no point doing this if there's nothing of substance to keep the new audience engaged with your profile. Like most things in life, it's all about balance.

6. The comments are ruthless

As someone who has received more than their fare share of revolting instagram DMs (and occasionally revolting LinkedIn Messages) I thought I'd be fine with TikTok comments - I was wrong! The comments are as brutal as any other platform I've been on which I wasn't expecting at all. The 'rude dudes' are a vocal minority and they are wildly outnumbered by wholesome and supportive users, but they exist nonetheless.

If your kids are posting on TikTok definitely check in with them and make sure they're ok!

7. The key to "The Algorithm" is UX

There's always so much talk about what "The Algorithm" prefers or pushes out to users, but the backbone of "The Algorithm" is a really interesting UX strategy.
On the 'for you page' where you can swipe through a stream of videos, there's only ever one video shown on screen at a given time. As a result, any user signals (eg how long someone watches a video, if they replay it, if they like/comment/share the video or if they click through to view more videos with the same audio or more videos from the same creator) can be directly tied back to that content.

This strategy is so simple but so effective!

It's very different to the 'explore' page on Instagram which can show ~17 pieces of content at the same time. If a user dwells on this page, there's no quick way to understand what they're actually pausing to look at, so it's impossible to tie this back to a reinforcement learning model to improve "The Algorithm".

This is something I talk with Blackbook.ai clients quite often. It's not about having the "fanciest" algorithm - it's about having good data to work with. For some clients this means modernising and de-risking their Data Warehouse/Data Lake and for other clients, this means optimising internal processes and UX of internal products to make it easy and intuitive to give feedback signals and improve the effectiveness of an AI solution.

TikTok is the best example of this I've seen 'in the wild' and it's a valuable take-home message even if you never intend on actually using the platform.

About the Author: Brooke Jamieson is the Head of Enablement - AI/ML and Data at Blackbook.ai, an Australian consulting firm specialising in AI, Automation, DataOps and Digital.
Learn more about Blackbook.ai here and learn more about Brooke here.