100 different channels and nothing on? Microsoft has just licensed semantic video discovery technology from Israeli startup Jinni to help you find the perfect movie.
At the heart of Jinni is a movie genome comparable to Pandora’s music genome, which categorizes video content and provides recommendations. Microsoft did not specify how the software will be used but it’s likely to be deployed to boost video services on the XBox gaming console which already allows access to Netflix. “As with many of our commercial deals, the customer first discovered Jinni as an end user of our website.” said CEO Yosi Glick. Jinni was previously selected as a partner for Google TV.
Most of us choose movies based on rather amorphous criteria like mood or an association with another movie we like. Categorizations like genre are too wide; titles are too specific. Jinni approaches discovery in an intuitive way. You can search for movies and TV shows based on mood terms like “witty”, “stylized” or “disturbing” or plot elements like “unlikely couple” or “ambition”. You can also tune results to request lesser known titles or faster paced content.
At the heart of Jinni is a movie genome similar to Pandora’s music genome that categorizes video content using 2,200 different parameters or “genes” covering mood, style, setting, atmosphere, etc. Jinni uses a combination of natural language processing and sentiment analysis to derive the genes from reviews and other information available online about a particular movie. A minimum of 4 reviews is required to analyze a title and even long-tail titles have typically been reviewed many more times. This method means that a title can be indexed even if it has never been watched by a Jinni user.The recommendation system learns your “movie personality” based on ratings you give to search results and expects to give high-quality personalized recommendations after 10-20 ratings.
The combination of algorithms used to extract the genes, determine their relevance and use them in recommendations is Jinni’s golden egg and a closely guarded secret. This is not an easy problem given the subtleties of language and meaning (“Is dark humour the same as irreverent humour?” “What is the distinction between assassin, serial killer and slasher?”) not to mention the unstructured nature of the online data which is used.
“Jinni’s strategy is to be every place consumers make a decision about what video content to watch – to be the engine inside leading digital video platforms.” concludes Glick. Jinni is based in Tel Aviv, was established in 2008, has 20 employees and received total funding of $8.1 million from the Startup Factory, DFJ Tamir Fishman Ventures and Belgian mobile carrier Belgacom.
VB's research team is studying web-personalization... Chime in here, and we’ll share the results.