OVGuide Updates Video Search and Discovery Tools

Online Video Guide is a comprehensive video search portal that draws results from sites including Fancast, Hulu, ESPN and Funny or Die.



















They claim to deliver the most relevant search results of any video engine because of their team of editors, who manually comb, categorize, and tag content. In these tough times, I wonder how long they can afford to ....

While video search hasn’t truly come into its own so far on major engines like Google, OVGuide does face several competitors hoping to do the same thing, including earlier players Blinkx, Truveo, and Meefeedia, according to paidContent.

OVGuide currently derives its revenue through ad partnerships with the likes of NBC, ABC, and Warner Brothers. Here is to wish them the best of luck to keep the ad dollars coming!

Is Jinni the Pandora of Movies?

Jinni.com, in beta now, is a search and recommendation engine built specifically for movies. So, what does this tech talk mean to the rest of us?



For starters, you can:

• Search with the engine that understands movies
• Get recommendations that fit your unique taste
• Explore the best of the multiplex and beyond
• Watch wherever you choose

How It Works - The Movie "Genome"

Inside, the "Genome" is broadly divided in two:

• Experience - the mood and tone of the content
• Story - plot elements (One man army, Battle of the sexes), structures (Nonlinear, Story-within-a-story), flags (Violence, Nudity, oohhh NO!) and more.

It also includes many external aspects like awards.

The starting point is manual tagging by Jinni's film professionals. Each title has around fifty "genes," among thousands of possibilities. Then, using advanced machine-learning technology, Jinni's system parses the manual tags to begin automated tagging. This creates a level of consistency that we ordinary humans can't reach - especially important for similarity matches and recommendations, which won't work unless you compare apples to apples and battles to battles as often as possible. Users who vote on "genes," along with the Jinni team, constantly check and improve the accuracy of machine tagging.

Recommendations

Jinni thinks the best recommendations use man and machine. A machine can deeply analyze the type of content you like, to learn about your unique taste. People can share their personal favorites and opinions about what they've seen (in a way no machine can do, as yet). Jinni isn't a social network, it's a service designed to fit how people experience media - and dialogues about movies and shows are part of that.

Jinni recommends by comparing YOUR Taste Types and the genes of all the titles in their catalogue, figuring in your preferences (movies or TV, in theaters or online) and some other filters. Simplistically, if you have the "genes" for Gloomy Love Triangles, they'll recommend titles with those dominant "genes." As a user, you receive recommendations from Jinni, your Movie Circle, your Neighbors (people Jinni identifies as having taste similar to yours), and your Groups.

While this all sounds great, hip, and cool, I'd drop "genes" and "genome" as describers of how Jinni is meant to work. "Simplistically speaking," they are confusing and unnecessary. At least to me.