Have you ever wondered how Two Hat maintains a dynamic and up-to-date chat filter in an ever-evolving world, in 20 languages?
In light of recent global events, including the COVID-19 pandemic and the #BlackLivesMatter movement, we wanted to provide insight into our internal process.
We spoke to Portuguese Language Specialist Richard Amante, a journalist with 15 years of international experience, about how he and the team stay on top of the latest news.
As Richard explains, the Language & Culture team researches trending topics and new linguistic expressions and adds them to the dictionary in multiple languages. It doesn’t end there.
After the team adds new expressions to the chat filter, they review and adjust how those expressions are used across different communities and in different contexts. That includes finding and fixing false positives (low-risk content incorrectly flagged as high-risk) and false negatives (you guessed it — high-risk content incorrectly flagged as low-risk), detecting new and unexpected linguistic patterns, and upgrading and downgrading the riskiness of a phrase based on cultural shifts.
Especially today, in a world where so many of us are stuck at home, the lines separating our “real life” from our “online life” are blurry, if they exist at all. Whether we’re forming a clan in a multiplayer game or commenting on a friend’s profile pic, we’re having conversations online about everything, from the latest news to pop culture.
You might be wondering — why does this matter? It’s simple. Our clients want to know what their players and users are talking about; and more importantly, they want to keep them safe from abuse, hate speech, and harassment — while still promoting healthy conversations.
Every online community has different standards of what a healthy conversation looks like. An edtech platform designed for 7-12-year-olds will likely have a different standard from a social network catering to millennials. Here is the great power of Two Hat’s Community Sift: While the Language & Culture team provides a baseline by adding new words and phrases to the dictionary, clients can augment those words and phrases in real-time, as needed.
In this way, we work closely with our clients to maintain a living, breathing global chat filter in an ever-changing world.
Want to learn how Two Hat can help you maintain a safe and healthy online community? Request a demo today.
In order for chat experiences to be considered “good” by the user in the first place though, you have to make sure that no users are excluded, bullied, or harassed away from your chat community and game before they ever get a chance to fall in love with it.
That said, it’s hard to deliver a consistently positive chat experience in one language fluently and with nuance, let alone in the world’s 20 most popular langauges. Add in leet aka 1337 and other ever-evolving unnatural language hacks and the task of scaling content moderation for global chat can be daunting.
With this shifting landscape in mind, Two Hat offers these 4 Musts for Safe In-Game Chat in any Language.
#1. Set expectations with clear guidelines Humans change our language and behavior based on our environment. The very act of being online allows for a loosening of some behavioral norms and often anonymity, so it’s important users understand the guidelines for behavior in your community. As you ponder how to establish these guidelines, remember that cultural norms around the world are very different.
In other words, what is a reasonable chat policy in one language or culture may be inappropriate in another.
#2. Develop unique policies for each culture
French is spoken fluently in Canada, Africa and the Caribbean, but the experiences of those places are entirely different.
Native speakers know these nuances, translation engines do not. Two Hat can provide accurate and customizable chat filters built and supported by our in-house team of native speakers of over 20 languages.
These filters must be on every gaming site and inside every mobile gaming app.
#3. Let user reputation be your guide
Users with a good reputation should be rewarded. Positive users are aligned with the purpose of your product, as well as your business interests, and they’re the ones who keep others coming back.
For those few who harass others – in any language – set policies that automate appropriate measures.
For example: set a policy requiring human review of any message sent by a user with 2 negative incidents in the last 7 days, etc. In this way, user reputation becomes the impetus behind in-game experience, democratizing user socialization.
#4. Tap your natural resources
In every language and in every culture the key to building opportunity is engaging your most committed players. The key to building safer and more inclusive in-game communities is the same.
Engaged, positive users empowered to flag and report negative experiences are the glue that binds in every language and culture.
Make sure each has a voice if they feel threatened or bullied or witness others being harassed, provide the community leaders that emerge with the tools and voice to be of positive influence, and build a chat experience that’s as cool and inclusive as your game works to be.
Is 2019 the year that content moderation goes mainstream? We think so.
Things have changed a lot since 1990 when Tim Berners-Lee invented the World Wide Web. A few short years later, the world started to surf the information highway – and we’ve barely stopped to catch our collective breath since.
The internet has given us many wonderful things over the last 30 years – access to all of recorded history, an instant global connection that bypasses country, religious, and racial lines, Grumpy Cat – but it’s also had unprecedented and largely unexpected consequences.
Rampant online harassment, an alarming rise in child sexual abuse imagery, urgent user reports that go unheard – it’s all adding up. Now that well over half of Earth’s population is online (4 billion people as of January 2018), we’re finally starting to see an appetite to clean up the internet and create safe spaces for all users.
The change started two years ago.
Mark Zuckerberg’s 2017 manifesto hinted at what was to come:
“There are billions of posts, comments, and messages across our services each day, and since it’s impossible to review all of them, we review content once it is reported to us. There have been terribly tragic events — like suicides, some live streamed — that perhaps could have been prevented if someone had realized what was happening and reported them sooner. There are cases of bullying and harassment every day, that our team must be alerted to before we can help out. These stories show we must find a way to do more.”
In 2018, the industry finally realized that it was time to find solutions to the problems outlined in Facebook’s manifesto. The question was no longer, “Should we moderate content on our platforms?” and instead became, “How can we better moderate content on our platforms?”
The good news is that in 2019, we have access to the tools, technology, and years of best practices to make the dream of a safer internet a reality. At Two Hat, we’ve been working behind the scenes for nearly seven years now (alongside some of the biggest games and social networks in the industry) to create technology to auto-moderate content so accurately that we’re on the path to “invisible AI” – filters that are so good you don’t even know they’re in the background.
As many of you know, Smyte was recently acquired by Twitter and its services are no longer available, affecting many companies in the industry.
As CEO and founder of Two Hat Security, creators of the chat filter and content moderation solution Community Sift, I would like to assure both our valued customers and the industry at large that we are, and will always remain, committed to user protection and safety. For six years we have worked with many of the largest gaming and social platforms in the world to protect their communities from abuse, harassment, and hate speech.
We will continue to serve our existing clients and welcome the opportunity to work with anyone affected by this unfortunate situation. Our mandate is and will always be to protect the users on behalf of all sites. We are committed to uninterrupted service to those who rely on us.
If you’re in need of a filter to protect your community, we can be reached at email@example.com.
“Chatting is a major step in our funnel towards creating engaged, paying users. And so, it’s really in Twitch’s best interests — and in the interest of most game dev companies and other social media companies — to make being social on our platform as pleasant and safe as possible.” – Ruth Toner, Twitch
But that begs the question — should you build it yourself or use an outside vendor? Like anti-virus software, it’s better left to a team dedicated day in, day out, to keeping the software updated.
A few things to consider before investing a great deal of time and expense into an in-house chat filter.
1. An allow/disallow list doesn’t work because language isn’t binary
Traditionally, most filters use a binary allow/disallow list. The thing is, language isn’t binary. It’s complex and nuanced.
For instance, in many older gaming communities, some swear words will be acceptable, based on context. You could build a RegEx tool to string match input text, and it would have no problem finding an f-bomb. But can it recognize the critical difference between “Go #$%^ yourself” and “That was #$%^ing awesome”?
What if your players spell a word incorrectly? What if they use l337 5p34k (and they will)? What if they deliberately try to manipulate the filter?
It’s an endless arms race, and your users have way more time on their hands than you do.
Think about the hundreds of different variations of these phrases:
“You should kill yourself / She deserves to die / He needs to drink bleach / etc” “You are a [insert racial slur here]”
Imagine the time and effort it would take to enter every single variation. Now add misspellings. Now add l337 mapping. Now add the latest slang. Now add the latest latest slang.
It never ends.
Now, imagine using a filter that has access to billions of lines of chat across dozens of different platforms. By using a third-party filter, you’ll benefit from the network effect, detecting words and phrases you would likely never find on your own.
2. Keep your team focused on building an awesome product — not chasing a few bad actors around the block
“When I think about being a game developer, it’s because we love creating this cool content and features. I wish we could take the time that we put into putting reporting [features] on console, and put that towards a match history system or a replay system instead. It was the exact same people that had to work on both who got re-routed to work on the other. – Jeff Caplin, Blizzard Entertainment
Like anything else built in-house, someone has to maintain the filter as well as identify and resolve specific incidents. If your plan is to scale your community, maintaining your own filter will quickly become unmanageable. The dev and engineering teams will end up spending more time keeping the community safe than actually building the community and features.
Compare that with simply tapping into the RESTful API of a service provider that reliably uses AI and human review to keep abusive language definitions current and quickly process billions of reports per day. Imagine letting community managers identify and effectively deal with the few bad actors while the rest of your team relentlessly improves the community itself.
3. Moderation without triage means drowning in user reports
There is a lot more to moderation than just filtering abusive chat. Filtering — regardless of how strict or permissive your community may be — is only the first layer of defense against antisocial behavior.
“Invest in tools so you can focus on building your game with the community.”
That’s Lance Priebe, co-creator of the massively popular kid’s virtual world Club Penguin, sharing one of the biggest lessons he learned as a developer.
Focus on what matters to you, and on what you and your team do best— developing and shipping kickass new game features.
4. It’s obsolete before it ships
The more time and money you can put into your core product — improved game mechanics, new features, world expansions — the better.
Think of it this way. Would you build your own anti-virus software? Of course not. It would be outdated before launch. Researching, reviewing, and fighting the latest malware isn’t your job. Instead, you rely on the experts.
Now, imagine you’ve built your own chat filter and are hosting it locally. Every day, users find new ways around the filter, faster than you can keep up. That means every day you have to spend precious time updating the repository with new expressions. And that means testing and finally deploying the update… and that means an increase in game downtime.
This all adds up to a significant loss of resources and time — your time, your team’s time, and your player’s time.
5. Users don’t only chat in English
What if your community uses other languages? Consider the work that you’ll have to put into building an English-only filter. Now, double, triple, quadruple that work when you add Spanish, Portuguese, French, German, etc.
Word-for-word translation might work for simple profanity, but as soon as you venture into colloquial expressions (“let’s bang,” “I’m going to pound you,” etc) it gets messy.
In fact, many languages have complicated grammar rules that make direct translation literally impossible. Creating a chat filter in, say, Spanish, would require the expertise of a native speaker with a deep understanding of the language. That means hiring or outsourcing multiple language experts to build an internal multi-language filter.
And anyone who has ever run a company knows — people are awesome but they’re awfully expensive.
How complex are other languages? German has four grammar cases and three genders. Finnish uses 15 noun cases in the singular and 16 in the plural. And the Japanese language uses three independent writing systems (hiragana, katakana, kanji), all three of which can be combined in a single sentence.
TL;DR:because grammar: Every language is complex in its own way. Running your English filter through a direct translation like Google translate won’t result in a clean, accurate chat filter. In fact, it will likely alienate your community if you get it wrong.
Engineering time is too valuable to waste
Is there an engineering team on the planet that has the time (not to mention resources) to maintain an internally-hosted solution?
Dev teams are already overtaxed with overflowing sprint cycles, impossible QA workloads, and resource-depleting deployment processes. Do you really want to maintain another internal tool?
If the answer is “no,” luckily there is a solution — instead of building it yourself, rely on the experts.
Think of it as anti-virus software for your online community.
Talk to the experts
Consider Community Sift by Two Hat Security for your community’s chat filter. Specializing in identification and triage of high-risk and illegal content, we are under contract to process 4 billion messages every day. Since 2012 we have been empowering gaming and social platforms to build healthy, engaged communities by providing cost-effective, purposeful automated moderation.
You’ll be in good company with some of the largest online communities by Supercell, Roblox, Kabam, and many more. Simply call our secure RESTful API to moderate text, usernames, and images in over 20 of the most popular IRL and digital languages, all built and maintained by our on-site team of real live native speakers.
“Chatting is a major step in our funnel towards creating engaged, paying users. And so, it’s really in Twitch’s best interests — and in the interest of most game dev companies and other social media companies — to make being social on our platform as pleasant and safe as possible.”
Today, let’s take a step back and uncover why filtering matters in the first place.
Filtering: First things first
Using a chat, username, or image filter is an essential technique for any product with social features. Ever find yourself buried under a mountain of user reports, unable to dig yourself out? That’s what happens when you don’t use a filter.
Every game, virtual world, social app, or forum has its own set of community guidelines. Guidelines and standards are crucial in setting the tone of an online community, but they can’t guarantee good behavior.
Forget about Draconian measures. Gone are the days of the inflexible blacklist/whitelist, where every word is marked as either good or bad with no room for the nuances and complexity of language. Contextual filters that are designed around the concept of varying risk levels let you make choices based on your community’s unique needs.
Plenty of online games contain violence and allow players to talk about killing each other, and that’s fine — in context. And some online communities may allow users to engage in highly sexual conversations in one-on-one chat.
For many communities, their biggest concern is hate speech. Users can swear, sext, and taunt each other to their heart’s content, but racial and religious epithets are forbidden. With a filter that can distinguish between vulgarity and hate speech, you can grant your users the expressivity they deserve while still protecting them from abuse.
“A user who experiences toxicity is 320% more likely to quit.” – Jeffrey Lin, Riot Games
Back in 2014, a Riot Games study found a correlation between abusive player behavior and user churn. In fact, the study suggested that users who experience abuse their first time in the game are potentially three times more likely to quit and never return.
In 2016 we conducted a study with an anonymous battle game, and interestingly, found that users who engaged in chat were three times more likely to keep playing after the first day.
While there is still a lot of work to be done in this field, these two preliminary studies suggest that social matters. Further studies may show slightly different numbers, but it’s well understood that negative behavior leads to churn in online communities.
When users chat, they form connections. And when they form connections, they return to the game.
But the flipside of that is also true: When users chat and their experience is negative, they leave. We all know it’s far more expensive to acquire a new user than to keep an existing one — so it’s critical that gaming and social platforms do everything in their power to retain new users. The first step? Ensure that their social experience is free from abuse and harassment.
Reduce moderation workload and increase user retention
Proactive filtering and smart moderation doesn’t just protect your brand and your community from abusive content. It also has a major impact on your bottom line.
Habbo is a virtual hotel where users from around the world can design rooms, roleplay in organizations, and even open their own trade shops and cafes. When the company was ready to scale up and expand into other languages, they realized that they needed a smarter way to filter content without sacrificing user’s ability to express themselves.
Friendbase is a virtual world where teens can chat, create, and play as friendly avatars. Similar to Habbo, the company launched their chat features with a simple blacklist/whitelist filter technology. However, chat on the platform was quickly filled with sexism, racism, and bullying behavior. For Friendbase, this behavior led to high user churn.
By leveraging a smarter, more contextual chat filter they were able to manage their users’ first experiences and create a healthy, more positive environment. Within six months of implementing new filtering and moderation technology, user retention by day 30 had doubled. And just like Habbo, user reports decreased significantly. That means fewer moderators are needed to do less work. And not only that — the work they do is far more meaningful.
Does your online community need a chat filter?
[postcallout title=”Thinking of Building Your Own Chat Filter?” body=”If you’re thinking about building your own chat filter, here are 5 important things to consider.” buttontext=”Read More” buttonlink=”https://www.twohat.com/thinking-building-chat-filter-4-reasons-youre-wasting-time/”]Ultimately, you will decide what’s best for your community. But the answer is almost always a resounding “yes.”
Many products with social features launch without a filter (or with a rudimentary blacklist/whitelist) and find that the community stays healthy and positive — until it scales. More users means more moderation, more reports, and more potential for abuse.
Luckily, you can prevent those growing pains by launching with a smart, efficient moderation solution that blends AI and human review to ensure that your community is protected from abuse and that users are leveraging your platform for what it was intended — connection, interaction, and engagement.
Are you unconvinced that you need a chat filter in your online game, virtual world, or social app? Undecided if purchasing moderation software should be on your product roadmap in 2018? Unsure if you should build it yourself?
You’re not alone. Many in the gaming and social industries are still uncertain if chat moderation is a necessity.
“Nothing normal ever changed a damn thing.” Slush, 2017
Now that’s a slogan.
It resonates deeply with us here in Canada. While sisu may be a uniquely Finnish trait, we’re convinced we have some of that grit and determination in Canada too. Maybe it’s the shared northern climate; cold weather and short, dark days tend to do that to a nation.
Regardless, it caught our eye. We like to go against the grain, too. And we’re certainly far from normal.
How could we resist?
On Thursday, November 30th and Friday, December 1st, we’re attending Slush 2017 in Helsinki, Finland. It’s our first time at Slush (and our first time visiting Finland), and we couldn’t be more excited.
It’s a chance to meet with gaming and social companies from all over the world — not to mention our Finnish friends at Sulake (you know them as Habbo) and Supercell.
At Two Hat Security, our goal is to empower social and gaming platforms to build healthy, engaged online communities, all while protecting their brand and their users from high-risk content. Slush’s goal is to empower innovative thinkers to create technology that changes the world.
#1 – Technology will not shape our future — we do.
Technology is no different from any other tool. A hammer can be used to harm, but it can also be used to build a home. In the same way, online chat can be used to spread hate speech, but it can also be used to make connections that enrich and empower us.
We have a chance to use technology as a force for change, not a weapon. This is our chance to embrace the fundamental values of fair play, sportsmanship, and digital citizenship and reshape gaming and social communities for the better.
Let’s use state-of-the-art technology and pair it with state-of-the-heart humanity to make digital communities better. Safer. Stronger. And hey, let’s be honest — more profitable. Better for business. (Profitable-er? That’s a word, right?)
Sharon and Mike will be hanging out at the Elisa booth, showing off our chat filter and moderation software tool Community Sift.
You can even test it out. This is your chance to type all the naughty words you can think of… for business reasons, of course.
Heading to Gamescom or devcom this year? It’s a huge conference, and you have endless sessions, speakers, exhibits, and meetings to choose from. Your time is precious — and limited. How do you decide where you go, and who you talk to?
Here are three reasons we think you should meet with us while you’re in Cologne.
You need practical community-building tips.
Our CEO & founder Chris Priebe is giving an awesome talk at devcom. He’ll be talking about the connection between trolls, community toxicity, and increased user churn. The struggle is real, and we’ve got the numbers to prove it.
Hope to build a thriving, engaged community in your game? Want to increase retention? Need to reduce your moderation workload so you can focus on fun stuff like shipping new features?
Chris has been in the online safety and security space for 20 years now and learned a few lessons along the way. He’ll be sharing practical, time-and-industry-proven moderation strategies that actually work.
We’re sending three of our very best Two Hatters/Community Sifters to Germany. Sharon has a wicked sense of humor (and the biggest heart around), Mike has an encyclopedic knowledge of Bruce Springsteen lore, and Chris — well, he’s the brilliant, free-wheeling brain behind the entire operation.
So, if you’d like to meet up and chat at Gamescom, Sharon, Mike, and Chris will be in Cologne from Monday, August 21st to Friday, August 25th. Send us a message at firstname.lastname@example.org, and one of them will be in touch.