We blend the best semantic technologies with the skill of our analysts to provide unique service: keywords are used just to manage priority in moderation queues.
A human person, experienced moderator, fluent in at least 2 languages, highly trained and with at least a college degree will READ each and every message and, from your dashboard, you can find out who dealt with each and every message and when (s)he did it.
We use deterministic algorithms to try to put policy infringing content on the top of the moderation queue and to actively moderate every message. At least once per day each message posted during the preceding 24 hours will be processed. We guarantee (you) a complete moderation run every 24 hours, although, under normal conditions, we are often able to process the moderation queue in just a few hours. We keep our moderators close to ourself: no "mechanical turkeys", but people being our greatest asset.
Social networks are undoubtedly one of the most powerful and most widespread ways to engage users online. With millions of users enrolled in modern social networks, more and more brands are engaging social platforms with an online presence and dedicated Fan spaces. In hight-traffic, deeply engaged social networks many brands feel the need to monitor and moderate the user-generated content to ensure its compliance with the brand’s identity and policies and to mitigate risks.
ConversationFlow offers a fully outsourced moderation service that allows you to take advantage of "real-people moderation" filters to block user-generated offensive, illegal, unsolicited or slanderous content from your social media platforms, through highly trained, college graduated human moderators supported by one of the most advanced social-network-moderation platforms. We have developed a comprehensive suite to take advantage of semantic processing, keyword filtering, distributed spam discovery and massively paralleled processing in order to get the most out of our moderators and to keep the pricing so low you cannot find an excuse NOT to sign up!
Policy and Procedures: We do not use automate filters for moderation, but only keywords to manage priority in moderation queues. We read each and every message and, from the dashboard, you can find out who managed each and every message, where and when.
We place on the top of the queue list and actively moderate (delete from your page):
- Content targeted at children or communities soliciting participation from kids and teens
- Obscene content and abusive or intimidating comments
- Copyright breaching content and intellectual property rights (copyrighted text, images, music or videos) Abusive comments against a user, the client customer, a minority, a group
- Inciting hate, violent, discriminative or libelous content
- Content raising child-protection issues (child abuse, bullying, personally identifiable information)
- Contenuti che violano la salvaguardia dei minori (abusi, bullismo, informazioni personali identificative)
- Unfair and aggressive contents, and spam (reiterated posting, non-sense comments, trolling, advertising, irrelevant or misused web links)
- Off topic comments
- Illegal content or links to illegal content
- Security alerts, including bomb and suicide threats.
Our standard procedure consists of:
- Moderation of standard contents
- Escalating direct inquires to the customer, using our Escalation procedure
- Deleting content against the aforementioned policy
- Escalating illegal content to the customer (or authorities)
We do not engage conversations directly or indirectly. We do not edit, improve, partially remove or modify any content.
Fond of technology and with an exceptionally deep technological background, we conceived, engineered and developed one of the most sophisticated and most performing moderation platforms on the market.
Our platform can easily moderate hundreds of thousands messages per hour from thousands of different pages, giving priority to the most critical messages, alerting moderators of potential security threats and most critical keywords in real time.
The platform can easily parallelize tasks, allowing moderators to work in a massively multiprocessing environment without encumbering each other. We are so confident in our platform that we are offering it as a service to Agencies and customers who would like to adopt the moderation within their own business, without using our moderators and allowing them to replicate our work-flow and policies to better suit their needs.
Everything under control: In every moment you can peek at our work in real time, using your personal dashboard to see every moderated message and every allowed content.
You can even comment on our moderation and suggest different strategies (for example allowing certain keywords).
We will get in touch with you when a message needs your attention and your response, for example, in case of:
- Direct queries about your brand
- Direct queries about your products or services
- Potentially useful submitted information
We call “escalation” this kind of alert, and when you answer an escalation you can choose to directly post your answer on your Page, without even having to log into the platform itself.
Do you think you're in need of custom-tailored services?
We can easily assist you in:
- Integrating Escalation with CRM Platforms
- Integrating Escalation with Trouble Ticket Systems
- Publishing content on your pages
- Moderating 10.000 to 1M messages per month
- Providing editorial services to populate your pages
- Providing a Dedicated Team for Online Customer Care
- Deploying a 24/7/365 moderation service with a guaranteed response-time of 30 minutes
...much much more!
Contact us for special inquiries and a Sales Representative will get in touch with you to find the best solution to your problems.