Spin-off: The Creative Data Interpreters

The ETH spin-off SpinningBytes programs software that use machine learning not only to analyze but also to understand huge amounts of data. It enables customised solutions to be developed for numerous IT problems and allows new insights to be gained from previously unused data.

Spin-off: The Creative Data Interpreters
Image Credit: Public Domain

Computer researchers at the ETH and Zurich University of Applied Sciences (ZHAW) have developed ETH spin-off SpinningBytes. They actually developed it in 2015 and published in scientific papers, but did not receive much popularity. Now, they have made it freely available on their homepage.

The spin-off offers fundamentally project related programming of data science software close by entire innovation arrangements.

CEO Mark Cieliebak said, “We develop programs that can analyze data and to a certain extent understand it. Our software looks at the existing data, produces statistics about certain regularities and generates new knowledge, which then guides it.”

When it comes to software building, the spin-off needs data on which to base the program and from which it can learn.

Spin-off: The Creative Data Interpreters
The software uses machine learning to create so-called word clouds, thus visualizing the linking of words in, for example, tweets. (Image: SpinningBytes)

One example involves classification and categorization of huge amounts of text. For example, the archive has been gathering writes about the Swiss economy since 1890, all of which are classified by a similar example. It even examined every text. It analyzed almost 30,000 categorized articles and also learned the assignment rules.

In addition, scientists have updated this spin-off so that it can recognize and understand the human voice and give an answer. These repetitive discussions could be automated by utilizing machine learning. In future, for instance, a medical institution could settle the primary institutionalized contact with potential clients utilizing an advanced frame.

Cieliebak sad, “However the software will not replace people. As soon as the conversation deviates too much from the standardized phrases, the software can no longer resort to automated responses and has to pass the customer on to a customer service representative.”

In another undertaking, one of the SpinningBytes’ projects utilizes tweets to research the danger of heart assault in various districts.

Cieliebak said, “Among other things, a heart attack has to do with whether you are happy or not. The language in the tweets allows conclusions to be drawn about levels of satisfaction, and by linking this to other statistical data, statements can be made about the heart attack risk in a particular area.”

Scientists are now planning for other prognostic programs.

The exhibition will be at stand T16, “Natürliche Sprache und künstliche Intelligenz” and experience how far research in this area has progressed.