Jinni is an Internet application that
was created to fit how people relate to movies and TV. The site includes tool that allow users to meet other people with shared tastes, compare preferences, and review and rank titles.
Search for plot keywords, such as "adoption" and Jinni will list films such as Juno, Big Daddy, Losing Iaiah, and so on. Search for a mood such as "suspenseful" and you'll be treated to films (with synopses) such as Bourne Ultimatum and Minority Report, as well as TV show such as Band of Brothers.
Click on a movie to find a plot summary, details on run time and cast, and user comments along with critical reviews. It's like IMDB.com, with a super-sized search engine.
To understand more about how this application works I interviewed Jinni co-founder Yosi Glick.
BE: Please tell us a bit about yourself, background, education, current position?
YG: I am the Co-founder and President of Jinni. My idea for Jinni grew from over a decade of experience in television, including at Oracle and at Orca Interactive as VP Marketing and Business Development. My educational background is in Information Systems: I have a B.S. from the Technion Israel Institute of Technology.
BE: How did Jinni.com come into being?
YG: While methods for getting movies / video into the hands of viewers have greatly advanced, methods for helping viewers figure out what they actually want to watch are lagging. In other words, we're overwhelmed with choice.
Genres (e.g. action, comedy), rather vague and stuffy categories originally designed for back-office cataloging, are still the favorite way of presenting options. In my decade of working in the TV industry, I saw how limited data prevents TV operators from designing more intuitive interfaces for their video-on-demand (VOD) offerings.
To create our holistic approach to content discovery, Jinni has an unusually diverse team of experts, including media industry professionals (film, TV, Internet), Psychology and world-class algorithm scientists in the areas of language processing and classifications.
BE: . How does the site work?
YG: Jinni takes an entirely new approach to choosing what to watch. We call our service a Taste Engine, because our focus is on understanding and satisfying people's personal tastes. Semantic search on Jinni is a flexible, mood-based approach to exploring (e.g. "thought-provoking sci fi" or "witty love story"), while recommendations are based on a unique profile of each person's taste.
For our public launch, we're also introducing some exciting new features around our innovative user taste profiling. The new Jinni Community includes features to identify users with similar tastes and to describe preferences you and others share. The “Movie Personality Sketch” is a (simplified) visual presentation of each user’s unique movie taste profile - and the basis for personalized recommendations.
Ultimately we see Jinni as the gateway to video entertainment: a one-stop-shop where people can choose and get linked to watch wherever and however they wish.
BE:. Who is the target audience?
YG: The target audience of Jinni.com is anyone who enjoys movies and TV, and is sometimes stumped for what to watch next. Our technology is sophisticated, yet our service is intended to be an easy, intuitive way to choose what to watch next based on your mood and tastes.
We also offer APIs to TV operators and Internet content providers, and are in advanced trial phases with several top tier companies.
BE: Please elaborate on the concept of Movie Personality.
YG: I sometimes ask people, "If you saw a user profile walking down the street, would you recognize it?" In the TV industry, people admit that they do not really know what a user profile looks like.
With our innovative approach to taste profiling, we are the first company to define a user profile for video entertainment. We call this "Movie Personality" because of its centrality and significance in understanding each user and providing a really personalized experience.
BE: . Tell us about the Movie Genome Project.
YG: Our Movie Genome contains several thousand genes, assigned to each title to describe plot, mood, style, setting, soundtrack and more. The Movie Genome is our core intellectual property and powers all the features on Jinni.
We index new titles by analyzing reviews and metadata, using innovative Natural Language Processing technology. This automated process offers consistency, a diversity of viewpoints (from analyzing many reviews) and of course efficiency.
Users on Jinni can vote on whether a given gene fits a given title, and we're planning to add more features for people to participate in the Movie Genome Project.
