How does the technology work?
United Robots use a combination of Artificial Intelligence (AI) and Natural Language Generation (NGL) to produce the texts from structured data sets. AI is used to choose the angle of the story, which NLG then writes the story – with possibly different angles depending on target audience. In addition, when a new language version is created we work with professional translators to get the idiomatic expressions correct for e g sports. This is not Google Translate – our texts read as if they were written by a journalist in their native language.
What kind of data can be used as a source for the editorial texts?
Any data that is structured and complete. In Sweden we use data from e g the sports result database Everysport, the Land Registry (for property sales) and Companies House (for registration of new local businesses). As long as the data is publically available and free to use, we can turn it into journalism. The limitation most often lies in what can be published on a news site.
Do readers notice that texts are written by a robot?
No. MittMedia asked readers who had just read an automatically generated text whether they had noticed it was written by a robot, and the large majority said that they hadn’t:
Are robots really taking over the journalists’ job?
The answer is no. In fact, the number of employees in local media houses has declined for many years, even without the use of automated content. Local media no longer cover local sports below a certain level in the league system. In most cases, the choice is not between a well-written text by a journalist, or an automated article produced by a robot. The choice is between a robot text, or no text at all.
What does a collaboration with United Robots look like from a publisher’s point of view?
At United Robots, we see ourselves as a service provider within the content automation field. We design, build and support the whole chain of actions required to get it up and running continuously within an organisation. Setting up an automated content generation process consists of several steps like data integration, data analysis, textual design, template creation, content generation, content analysis, content integration with the client’s receiving CMS, continuous improvements to tools, support, monitoring of client’s receiving and sending systems and more.
How is United Robots different from automated data-to-text tools like Wordsmith?
Wordsmith from Automated Insights is perhaps the most well known tool that lets anyone automate content based on structured data. Writing templates that takes data from a spreadsheet file and transforms that into text snippets is relatively straight forward for a person with some basic technical know how. Building more advanced narratives will quickly become overwhelming and become more like writing programming code and less like writing text. You will be forced to create a lot of tools and system on top of Wordsmith to get the results you want.
United Robots have a similar tool to Wordsmith’s to design and manage text templates, but there are so many more aspects to building content automation solutions than the writer tool. It's only one link in the chain. We have summarised some of them below.
(More extensive explanations in our technical white paper here.)
1. United Robots are experts in analyzing data, to produce newsworthy content. We work with multiple sources to build our insights. One example is when we produce real estate transaction articles. There we use the raw data from the real estate authority in Sweden, we then combine this data with two different geographical databases to be able to build insights like "Two weeks ago another property on the same street was sold for half the price" or "This is the top 10 most expensive properties sold this year on these three different beach strips".
2. We believe we have the most feature rich template design tool on the market. When writing a text we can for example consider whether something has already been mentioned in a previous text segment. An example is if we have written about John Doe having scored 10 goals in the game, we ensure that we don't repeat this in the next segments.
3. United Robots has extensive experience in delivering automated content to media companies. Besides analysing data and designing robot text templates we have a set of features specifically targeted to media companies. For example when writing about sports, we produce one version from the home team's perspective, one from the away team’s perspective and one with a neutral perspective.
4. The technical infrastructure is based on a serverless and completely cloud based architecture, allowing us unlimited parallelism and a very cost efficient through-put. A typical text takes around one second to generate, and we will be completely linear when scaling this. If we do 100 texts at the same time, they all will complete after that same second. Also since the actual text generation is so cost efficient, we can basically regenerate texts in real time.
5. We are not selling a tool. We provide a service where we take responsibility of working with our partners to continuously improve the automated content feeds that have been built. We analyse the generated texts in retrospect for correctness and variability as well as use feedback from our partners to prioritise which areas should be given focus in the next evolutionary step.