More on Twitter’s Machine Learning Initiatives
By looking at job posts, you can sometimes learn a lot: in this case, it’s about where Twitter may be headed with its artificial intelligence work.
The company has reportedly been applying machine learn to its advertising systems and towards helping Twitter remove objectionable material from the network. But now, the company is looking to expand these applications into improving the way it makes content discoverable to users.
A goal of Cortex appears to be “automatic content understanding.” A job listing explains that Twitter basically building the “backbone” of its learning systems, which are intended to automatically label the flood of disparate content that users publish on its social network.
Here’s how Twitter explains in the job listing why it needs artificial intelligence and how it views the new Cotex team:
Twitter is a unique source of real-time information, offering amazing opportunities for automatic content understanding. The format of this content is diverse (tweets, photos, videos, music, hyperlinks, follow graph, …), the distribution of topics ever-changing (on a weekly, daily, or sometimes hourly basis), and the volume ever-growing; making it very challenging to automatically and continuously expose relevant content. Manually defining features to represent this data is showing its limits.
#semantic #AI #machinelearning #twitter
cc: Mark Traphagen David Amerland