Connect with us

SOCIAL

YouTube Shares Overview of its Content Recommendation Systems, and the Key Factors that Define Reach

Published

on

YouTube has published a new overview of how its content recommendations system works, which is one of the central drivers of video reach and views on the platform, and may help YouTube marketers get a better understanding of what guides optimal response.

YouTube actually published a similar overview earlier in the year, as part of its ongoing effort to maximize transparency, with this new explainer giving a little more historical insight as to how its systems have evolved, and how it’s working to improve its processes.

As explained by YouTube:

Our recommendation system is built on the simple principle of helping people find the videos they want to watch and that will give them value.”

Of course, ‘value’ is a fairly vague term in social media metrics, and especially in measurement, but the idea, according to YouTube, is to show people more of what they like, based on not only their own behaviors, but other, similar users as well.

“You can find recommendations at work in two main places: your homepage and the “Up Next” panel. Your homepage is what you see when you first open YouTube – it displays a mixture of personalized recommendations, subscriptions, and the latest news and information. The Up Next panel appears when you’re watching a video and suggests additional content based on what you’re currently watching, alongside other videos that we think you may be interested in.

YouTube Recommendations surfaces

The ‘Up Next’ panel has been one of the more scrutinized elements of the platform in recent years, with some users saying that these recommendations can lead them down conspiracy-fueled rabbit holes, and even radicalize them based on the content they find.

So how might that happen?

Here are some of the key notes on exactly how YouTube’s recommendations process works.

Foundationally, YouTube’s recommendations are based on four key elements:

  • Clicks  The videos you click on provide YouTube with a direct indicator of your interest in the content. But it’s not always the thing that defines your experience. For example, you might click through on a video looking for something, then not find it in that specific clip, so that click, in itself, is not a strong indicator of what you want. Which is why YouTube also measures ‘Watchtime’ as an additional qualifier. 
  • Watchtime As it sounds, watchtime measures how long you actually watch each video you click on for, which helps YouTube recommend more specific content aligned with your interests: “So if a tennis fan watched 20 minutes of Wimbledon highlight clips, and only a few seconds of match analysis video, we can safely assume they found watching those highlights more valuable.”
  • Sharing, Likes, Dislikes YouTube also measures your share and like activity, another direct response measurement in the app. “Our system uses this information to try to predict the likelihood that you will share or like further videos. If you dislike a video, that’s a signal that it probably wasn’t something you enjoyed watching.”
  • Survey Responses Finally, and in addition to these explicit response indicators, YouTube also conducts regular viewer surveys to find out if users are having a good experience in the app. For example, if you watch a clip for 20 minutes, YouTube may ask you if you enjoyed the clip, and to give it a star rating to better guide its recommendation systems.

All of these elements you likely could have guessed would be factored in, so there’s no major insight, necessarily. Though it is also interesting to note that YouTube additionally seeks to help you find content that you might not even know exists, based on the content that other people with similar viewing profiles to you watch.

“So if you like tennis videos and our system notices that others who like the same tennis videos as you also enjoy jazz videos, you may be recommended jazz videos, even if you’ve never watched a single one before.”

That’s likely how people come across those conspiracy theory trails – you look up one video on a topic that you’re interested in, then YouTube hits you with a range of related viewing that other people have watched as a result. If you fall into the wrong viewer profile, that could lead to a host of questionable stuff – though YouTube does also note that it is working to address such recommendations, and limit exposure to what it identifies ‘low quality content’.

So what qualifies as ‘low quality’ in this context?

“We’ve used recommendations to limit low-quality content from being widely viewed since 2011, when we built classifiers to identify videos that were racy or violent and prevented them from being recommended. Then in 2015, we noticed that sensationalistic tabloid content was appearing on homepages and took steps to demote it. A year later, we started to predict the likelihood of a video to include minors in risky situations and removed those from recommendations. And in 2017, to ensure that our recommendation system was fair to marginalized communities, we began evaluating the machine learning that powers our system for fairness across protected groups – such as the LGBTQ+ community.

In addition to these, YouTube also bans content that includes false health claims (like COVID conspiracy clips), while it’s also taking more steps to address political misinformation. Some of this type of material still gets through, of course, but YouTube is working to improve its systems to ensure that such material is not recommended via its discovery tools.

A key consideration in this element relates to “authoritative” or “borderline” content.

In seeking to limit the reach of borderline clips – those that don’t necessarily break the platform’s rules, but do present potentially harmful material – YouTube uses human evaluators to assess the quality of information in each channel or video.

“These evaluators hail from around the world and are trained through a set of detailed, publicly available rating guidelines. We also rely on certified experts, such as medical doctors when content involves health information.”

To determine ‘authoritativeness’, YouTube says that its evaluators answer a few key questions:

  • Does the content deliver on its promise or achieve its goal?
  • What kind of expertise is needed to achieve the video goal?
  • What’s the reputation of the speaker in the video and the channel it’s on?
  • What’s the main topic of the video (eg. News, Sports, History, Science, etc)?
  • Is the content primarily meant to be satire?

YouTube’s evaluators assess the reputation of a channel/creator based on a range of qualifiers, including online reviews, recommendations by experts, news articles and Wikipedia entries (you can check out the full listing of potential qualifiers here).

All in all, the system is designed to utilize explicit and implicit signals to highlight more of what each person wants to see, while also filtering out the worst kinds of content, in order to limit potential harm. The actual specifics of harm are a factor in this calculation, and limiting that reach – but again, YouTube says that it is working to update its recommendation tools to ensure higher quality content, based on these qualifiers at least, ends up getting more exposure in the app.

YouTube has also shared this overview of how its recommendations algorithms have evolved over time.

YouTube Recommendations development history

In assessing the various measures from a marketing and performance perspective, the key consideration is audience response, and creating content that appeals to your target viewers.

You can measure this in your YouTube analytics, and with users able to directly subscribe to your channel, there are some strong, key indicators that you can use to assess your performance, and ensure you’re aligning with viewer interests. That will then see your content also shown to other people with similar audience traits, while ensuring that you have a good website reputation, and a strong general web presence, will also limit potential penalties in YouTube moderators’ assessment.

It’s also worth checking your content against the above listing of ‘authoritativeness’ as a quick measure that you’re adhering to YouTube’s goals.

None of these elements will guarantee ultimate reach success, but failing to tick the right boxes will limit your potential. It’s worth noting these keys, and considering each aspect in your marketing effort.

Socialmediatoday.com

SOCIAL

Reports Show that Facebook Usage is Up, as Meta Continues to Develop its AI Targeting Models

Published

on

Reports Show that Facebook Usage is Up, as Meta Continues to Develop its AI Targeting Models

While Facebook is no longer the cool app, especially among younger audiences, it remains a key platform for many users, and its capacity to keep people updated on important updates from friends and family is likely to ensure that many continue to return to the app every day for some time yet.

But more than that, Facebook usage is actually increasing, according to internal insights viewed by The Wall Street Journal, which also include some interesting notes on overall Facebook and Instagram usage trends.

As per WSJ:

Data gathered in the middle of the fourth quarter showed that time spent on [Facebook] was up worldwide, including in developed markets, over the course of a year.”

Which seems unusual, given the subsequent rise of TikTok, and short form video more generally. But actually, Facebook has been able to successfully use the short-form video trend to drive more usage – despite much criticism of the platform’s copycat Reels feature.

Indeed, Reels consumption is up 20%, and has become a key element in Meta’s resurgence.  

How is it finding success? Increased investment in AI, which has driven big improvements in the relevance models that fuel both Reels and its ads, which are also now driving better response.

On Reels, Meta’s systems are getting much better at showing users the Reels content that they’re most likely to be interested in. You’ve likely noticed this yourself – what was initially a mess of random clips inserted into your Facebook feed has now become more focused, and you’re probably finding yourself expanding a Reels clip every now and then, just to see what it’s about.

Reels has actually been too successful:

“Because ads in Reels videos don’t currently sell for as much as those sold against regular posts and stories, Reels’ growing share of content consumption was denting ad revenue. To protect the company’s earnings, the company cut back on promoting Reels, which lowered watch time by 12%.

So again, while Meta has been criticized for stealing TikTok’s format, it’s once again shown, just as it did with Stories, that this is a viable and beneficial pathway to keeping users engaged in its apps.

You might not like it, but replication works in this respect.

But for marketers, it’s likely the development of Meta’s AI targeting tools for ads that’s of most interest.

Over time, many performance advertisers have been increasingly recommending that marketers trust Meta’s AI targeting, with newer offerings like Advantage+ driving strong results, with far less manual targeting effort.

Advantage+ puts almost total trust in Meta’s AI targeting systems. You can choose a couple of targeting options for your campaigns, but for the most part, the process is designed to limit manual impact, in order to let Meta’s systems determine the right audience for your ads.

Which may feel like you’re ceding too much control, but according to Meta, its continued AI investment is now driving better results.

Heavy investment in artificial intelligence tools has enabled the company to improve ad-targeting systems to make better predictions based on less data, according to the interviews and documents […] That, along with shifting to forms of advertising less dependent on harvesting user data from off its platforms, are key to the company’s plans to overcome an Apple privacy change that restricted Meta’s capacity to gather information about what its users do outside its platforms’ walls, the documents show.”

That’s likely worth considering in your process, putting more trust in Meta’s targeting systems to drive better results. At the least, it may be worth experimenting with Meta’s evolving AI for ad targeting. 

It’s not all good news. Meta also notes that while time spent in its apps is on the rise, creation and engagement is declining, with fewer people posting to both Facebook and Instagram than they have in the past.

That’s particularly true among younger audiences, while notably, usage of Instagram Stories is also in decline, down 10% on previous levels.

So while Meta is driving more engagement from Reels, which draws on content from across the app, as opposed to the people and Pages you follow, that’s also led to a decline in user posting.

Is that a bad thing? I mean, logically, engagement is important in keeping people interested in the app, and Meta also relies on those signals to help refine its ad targeting. So it does need users to be sharing their own content too, but if it can get more people spending more time in its apps, that will help it maintain advertiser interest.

In essence, despite all of the reports of Facebook’s demise, it remains a key connective platform, in various ways, while Meta’s improving ad targeting systems are also helping to drive better results, which will keep it as a staple for brands moving forward.

If you were thinking of diversifying your social media marketing spend this year, maybe don’t reduce Facebook investment just yet.

Source link

Continue Reading

SOCIAL

Effective Ways To Personalize Your Customer Touch Points Even More In 2023

Published

on

Effective Ways To Personalize Your Customer Touch Points Even More In 2023

Will 2023 be the year of personalization? Consumers hope so. For the past two years, shoppers have been craving the personal touch: In 2021, McKinsey & Company noted that 71% of customers expected companies to deliver personalization. In 2022, a Salesforce survey found that 73% of people expected brands to understand their needs and expectations. So, this year is looking like one where personalization can no longer be seen as a “nice to have.”

The problem, of course, is how to get more personalized. Many companies have already started to dabble in this. They greet shoppers by name on landing pages. They rely on CRMs and other tools to use historical information to send shoppers customized recommendations. They offer personalized, real-time discounts to help buyers convert their abandoned shopping cart items to actual purchases.

These are all great ideas. The only problem is that they’ve become widespread. They don’t move the needle on the customer experience anymore. Instead, they’re standard, expected, and kind of forgettable. That doesn’t mean you can afford to stop doing them. It just means you must devise other ways to pepper personalization throughout your consumer interactions.

If you are scratching your head on how to outdo 2022’s personalization in 2023, try implementing the following strategies:

1. Go for full-blown engagement on social media.

One easy way to give the personal touch is through your social media business pages. Social media use just keeps growing. In 2022, there were about 266 million monthly active users (or MUAs) on Facebook, one billion on Instagram, and 755 million on TikTok. Not all these active users will fall into your target audiences, but plenty of them will.

Make engaging with your social followers one of this year’s goals. People spend a lot of time on social media. It’s where many of them “live,” so it only makes sense that it should be a place to drive personalization.

One quick way to ratchet up your company’s personal touch on social media is to personalize all your retargeted ads. Quizzes can also offer a chance for personalization. Simply set up an engaging quiz and allow people to share their results. It’s a fun way to build brand recognition and bond with consumers. Of course, there’s nothing wrong with going very personal and answering all comments. Depending on your team’s size and the number of comments you receive, this might be a viable option.

2. Leverage AI to go beyond basic demographics.

Most companies rely on customer demographic information to bolster personalization efforts. The only trouble with this tactic is that demographics can’t tell the whole story. It’s impossible to get a lot of context about individual users (such as their lifestyles, personal preferences, and motivators) just from knowing their age, gender, or location. Though demographic data is beneficial, it can cause some significant misses.

Michael Scharff, CEO and cofounder of Evolv AI, explains the workaround for this problem: “The most natural, and therefore productive, personalization efforts use demographics as a foundation and then layer in user likes, dislikes, behaviors, and values.”

You can leverage AI’s predictive and insightful capabilities to uncover real-time user insights. Scharff recommends this technique because it allows you to stay in sync with the fast-moving pace of consumer behavior changes. He adds that AI can be particularly beneficial with the coming limits to third-party cookie access because it can be a first-party data source, allowing you to maintain customer knowledge and connection.

To flesh out your organization’s strategy, look to other companies that have gone beyond demographics. Take Netflix, for example, which constantly tweaks its AI algorithm to help improve personalized content recommendations. Bottom line? Going deeper than surface information makes all the sense in the world if you want to show customers you know them well.

3. Keep your data spotless.

The better your data, the better your personalization efforts. Period. Unfortunately, you are probably sitting on a lot of unstructured or otherwise tricky-to-use (or impossible-to-use) data. One recent Great Expectations survey revealed that 77% of data practitioners have data quality problems, and 91% say that this is wreaking havoc on their companies’ performance.

You can’t personalize anything with corrupt or questionable data. So, do your best to find ways to clean your data promptly and routinely. For example, you might want to invest in a more centralized data system, particularly if the personalization data you rely on is scattered in various places. Having one repository of data truth makes it easier to know if the information on hand is ready to use.

Another way to tame your data is to automate as many data processes as possible. Reducing manual manipulation of data lessens the chance of human error. And you’ll feel more confident with all your personalization efforts if you can trust the reliability and health of your data.

4. Go for nontechnical personalization.

It’s the digital age, but that doesn’t mean every touchpoint has to be digitized. Consumers often react with delight and positivity when they receive personalization in decidedly nontech forms. (Yes, you can use tech to keep track of everything. Just don’t make it part of the actual personalized exchange!)

Consider writing handwritten thank-you notes to customers after they’ve called in for support or emailed your team, for instance. Or send an extra personalized gift to buyers who make a specific number of purchases. These interactions aren’t technical but can differentiate your customer experience from your competitors’ experiences.

A groundbreaking Deloitte snapshot taken right before the pandemic showed that people were hungry for connection. By folding nondigital experiences into your personalization with customers, you’re showing them that you see them first as valued humans. That’s compelling and appealing, making them more apt to give you their loyalty in return.

Putting a personal spin on all your consumer interactions takes a little time. It’s worth your energy, though. You’ll wind up with stronger brand-buyer connections, helping you edge ahead of your competitors even more.

Source link

Continue Reading

SOCIAL

Planning for 2023: What Social Media Marketers Need to Win in 2023

Published

on

Planning for 2023: What Social Media Marketers Need to Win in 2023

January is, for many, a month of reflection, goal-setting, strategizing and planning for the year ahead. 

In line with this, we’ve kicked off the new year with a series of articles covering the latest stats, tips and strategies to help social media marketers build an effective game plan for 2023.

Below, you’ll find links to our 2023 social media planning series, which includes:

  • Content strategy guidelines to help you define your brand’s content mission and set SMART goals
  • Organic posting tips for Facebook, Instagram, TikTok, Twitter, LinkedIn, Snapchat and Pinterest 
  • Explainers on how to research key topics of interest in your niche, understand the competitive landscape, and help you find your audience and connect with them where they’re active
  • A holiday calendar and notes on the best days and times to post to each of the major platforms

 

Source link

Continue Reading

Trending

en_USEnglish