Connect with us

SOCIAL

Instagram Shares New Insights into How it Selects Recommended Posts to Highlight in User Home Feeds

Published

on

Instagram Shares New Insights into How it Selects Recommended Posts to Highlight in User Home Feeds

Looking to get a better handle on how Instagram’s feed algorithms work, and how you can optimize your content approach accordingly?

You’re in luck – today, Instagram has published a new overview of how it ranks content for its ‘Suggested Posts’, or the posts that you see in your Home feed from accounts that you don’t follow in the app.

This element became a key focus recently, after Instagram began inserting a lot more AI-based content recommendations into user feeds, which prompted widespread user backlash, and has since seen IG scale it back, as it works to refine its algorithms. But even with that shift, Instagram does see AI recommendations as a key element of its future, and in maximizing user engagement.

In other words, even if you’re not seeing as many recommendations in your home feed right now, they will be ramping up again sometime soon.

So how does Instagram select which additional content to show you in your Home feed? Here are some insights:

First off, Instagram’s engineering team outlines the focus of its recommendation system, and underlines the key aims of its approach:

  • Users spend a lot of time crafting the perfect home feed for themselves. How can we do some of that work for them and make it feel like they crafted these recommendations themselves?
  • Anecdotally speaking, users who stay engaged keep finding newer sources of interests to follow. Can we help in this act of progressive personalization a bit?

Whether people actually want an automated system to do this work for them is another question entirely, but the intended aim is to replicate human discovery with AI features, in order to enhance user engagement.

That then sees Instagram’s post recommendations fall into two categories – ‘Connected’ and ‘Unconnected’, with the latter being the posts that Instagram’s systems find and highlight, based on your interests.

The process, as you would expect, is largely based on implicit signals – i.e. actions you’ve directly taken in the app, like following and liking posts. But it can also extend to the people you follow, and what they like, as a proxy for direct engagement, while some popular posts are also highlighted based on overall engagement.

But these elements are more related to its Explore surface – in the Home feed, the aim is to replicate the feel of the posts and profiles that you’ve chosen to follow, in order to make it increasingly familiar.

Scrolling through the End of Feed Recommendations should feel like scrolling down an extension of Instagram Home Feed.

Instagram algorithm overview

That’s important to note – the recommendations that Instagram wants you to see in your main feed should closely replicate the accounts that you follow, down to the types of posts they share. At the same time, Instagram’s also trying to insert more and more video – specifically Reels – into user feeds, which is another factor in its more recent experiments.

But the aim, as noted, is to build more directly on your stated interests, as opposed to simply adding in the latest trending content.

So how does Instagram do that?

“In order to ensure that our recommendations feel similar to posts in Home Feed we prioritize accounts that are similar to accounts a user encounters in Home.

  • In the candidate selection step while training and evaluating our ranking models we ensure that the overall distribution is not skewed away from Home-based sources.
  • We follow the same freshness and time sensitivity heuristics as Home Feed to ensure that suggested posts provide a similar kind of fresh feeling as the rest of Home Feed.
  • We also ensure that the mixture of media types (like photos/videos/albums etc.) are relatively similar in Home and suggested posts.
  • For users whose immediate engagement graph is relatively sparse, we generate candidates for them by evaluating their one-hop and two-hop connections. Example: If user A hasn’t liked a lot of other accounts, we can probably evaluate the accounts followed by the accounts A has liked and consider using them as seeds. A → Account Liked by A → Accounts followed by the accounts A likes (Seed Accounts). The diagram below visualizes this line of thinking.

Key points for marketers:

  • Instagram tries to recommend content which is similar to the accounts that people have chosen to follow, so it may be worth conducting more research into what other brands in your industry, particularly those that are doing well on IG, are posting, in order to better align with the specific elements that could then see your content highlighted to your target consumers
  • ‘Freshness’ is important, which means that you need to be posting regularly to ensure that you’re maximizing your opportunities in this respect
  • Worth also noting that Reels is becoming a bigger focus over time, so while it’s not explicitly stated here, as more users engage with Reels, more Reels will, in turn, be recommended in Home feeds

There’s not a heap of nuggets to latch onto here, but the key point is that Instagram wants its Home feed recommendations to feel familiar to each user, so it’s less about highlighting the latest viral hits from across the app, and more about aligning with each users’ explicit interests.

That, in itself, could be very valuable insight for your IG approach.

You can read the full research post here.

Source link

SOCIAL

Twitter Tests Expanded Emoji Reaction Options in DMs

Published

on

Twitter Tests Expanded Emoji Reaction Options in DMs

Twitter’s looking to give users a broader set of emoji reactions for their DMs, while also, potentially, enabling personalization of your quick reactions display in the app.

As you can see in these mock-ups, shared by Twitter designer Andrea Conway, Twitter’s testing a new search option within the reaction pop-up in DMs which would enable you to use any other emoji as a reaction to a message.

An extension of this would also be the capacity to update the reactions that are immediately displayed to whatever you choose.

Twitter DM reactions

It’s not a game-changer by any means, but it could provide more ways to interact via DMs, and with more interactions switching to messaging, and more private exchanges, it could be a way for Twitter to better lean into this trend, and facilitate a broader array of response options in-stream.

Twitter’s working on a range of updates as it looks to drive more engagement and usage, including tweet view counts, updated Bookmarks, a new ‘For You’ algorithm, and more. Elon Musk has said that he can envision Twitter reaching a billion users per month by next year, but for that to happen, the platform needs to update its systems to show people more of what they like, and keep them coming back – which is what all of these smaller updates, ideally, build to in a broader approach.

But that’s a pretty steep hill to climb.

Last week, Twitter reported that it’s now up to 253 million daily active users, an increase on the 238 million that it reported in July last year. Daily and monthly active usage is not directly comparable, of course, but when Twitter was reporting monthly actives, its peak was around 330 million, back in 2019.

Twitter MAU chart

As noted in the chart, Twitter switched from reporting monthly active users to daily actives in 2019, but looking at the two measurements, it’s hard to imagine that Twitter’s monthly active usage is any more than 100m over its current DAU stats.

That means that Twitter has likely never reached more than 350 million active users – yet Musk believes that he can best that by close to 200% in a matter of months.

Seems unlikely – even at current growth rates since Musk took over at the app, Twitter would only be looking at around 500 million users, optimistically, by the end of 2024.

If it can maintain that. More recent insight from Twitter has suggested that user activity has declined since those early post-Musk purchase highs – but maybe, through a range of updates and tweaks, there could be a way for Musk and Co. to maximize usage growth, beyond what seems possible, based on the stats.

We’ll find out, and as it pushes for that next level, you can expect to see more updates and tweaks like this, with enhanced engagement in mind.  



Source link

Continue Reading

SOCIAL

Tarte Influencer Marketing Criticized 01/31/2023

Published

on

Tarte Influencer Marketing Criticized 01/31/2023

With consumers obsessed over the price of a dozen eggs, could conspicuous consumption-driven influencer marketing falling out of favor? That is the question brands might be considering after the
backlash that cosmetics brand Tarte is receiving after a sponsored trip to Dubai. “Influencers were called out for appearing not …

Read the whole story at Marketing Brew »



Source link

Continue Reading

SOCIAL

Twitter Applies for US Licenses to Facilitate In-App Payments

Published

on

Twitter Applies for US Licenses to Facilitate In-App Payments

Twitter has taken its next steps towards facilitating payments in the app, with The Financial Times reporting that the company has begun applying for regulatory licenses in US states, the next legal requirement for providing payment services in the app.

Payments, which Elon Musk has a long history in, could be another way for Twitter to generate revenue, by enabling transactions between users, from which it would then take a small percentage. Musk has repeatedly flagged his vision for payments as part of his broader push to make Twitter into an ‘everything app’, which would provide more functionality and usage benefits.  

As reported by FT:

In November, Twitter registered with the US Treasury as a payments processor, according to a regulatory filing. It has now also begun to apply for some of the state licenses it would need in order to launch, these people said. The remainder would be filed shortly, in the hope that US licensing was completed within a year, one of the people said.”

From there, Twitter would also look to establish agreements with international regulators to enable payments in all regions.

As noted, payments are a part of Elon’s broader plans for a more functional app, which would replicate the utility of China’s WeChat, which is used by Chinese citizens for everything from ordering groceries, to buying public transport tickets, to paying bills, etc. WeChat has become such a crucial connective element, that it formed a key part of China’s COVID response, with authorities using the app as a means to manage COVID positive citizens and restrict their movement.

Musk isn’t ideally looking to use Twitter as a control device (I don’t think), but the broader concept is to add in more and more functionality, in order to both generate more income for the company, and make the app a more critical element in the interactive landscape.

Twitter’s already exploring several options on this front.

Several app researchers have uncovered mock-ups for Twitter Coins in the back-end of the app.

Via Twitter coins, users would be able to make donations to creators in the app, through on-profile tipping, but beyond that, Twitter’s also exploring options like unlockable tweets, paywalled video, and more, as it seeks to embed broader usage and adoption of in-app payments.

A big opportunity also exists to facilitate remittance, or sending money to family and friends, which is a key use case in many regions. Remittance payment services often charge processing fees, and various social apps have been trying to find new ways to facilitate such without the same costs, with the idea being that once people are moving their money in-app, they’ll then be more likely to spend it in the same place.

Thus far, social platforms that do offer payments haven’t been able to embed this as a use case – but maybe, with Musk’s experience, knowledge and connections, he might be able to make this work in tweets.

Elon, of course, got his start in payments, with his first company, an online bank called X.com, being bought out by PayPal in 1999, his first big business win. And while his focus has since shifted to electric cars and rockets, Musk has keen understanding of the digital payments space, and how it can be adapted for varied usage.

According to reports, Musk told Twitter investors in May last year, that his aim was to see Twitter bring in about $1.3 billion in payment revenues by 2028.

That would give the company a sorely needed boost. After Musk’s cost-cutting efforts, which have resulted in the reduction of around 70% of Twitter staff, the company could be on track to potentially break even this year, or close, but a lot has to go right to get the platform back on track. And with advertisers continuing to back away from Twitter spend, it’s not looking good, while subscriptions to Twitter Blue are unlikely to provide much relief, at least at this stage.

As such, the shift into payments can’t come fast enough, though it’ll still be some time before we see the possibility of in-app payments.

Also, while Musk has made it clear fiat currency will be the main focus of this push in its initial phase, cryptocurrencies could also, eventually, be included. The price of Dogecoin, Musk’s favorite crypto offering, rose to a 24-hour high after news broke of Elon’s expanded payments plan.

Will payments be the answer to Twitter’s revenue woes? Maybe, if Elon’s vision for billions in payments revenue comes to fruition – and with his previous track record, you can’t dismiss the notion entirely.

But it’ll take time, many approvals, and many more steps before we reach the next stage.

Source link

Continue Reading

Trending

en_USEnglish