Yelp is the juggernaut of food and entertainment reviews but there’s always room for a little guy to move in and do things better. A service called Loku finds news and recommends places in neighborhoods based on its algorithms that apply natural language processing and sentiment analysis to the reviews, posts, and social media updates it reads. Essentially, it looks at a neighborhood and figures out how to characterize it. Then, it bases the recommendations it shows you on the content and tone of the reviews left for venues relative to the character of the neighborhood.
So, for example, when going to higher end places, places with reviews that call something “elegant” will be promoted more than venues with reviews containing words like “grungy” or “rad.”
We’ll have to wait and see if they can make this profitable. Right now their money comes from linking to Groupon/LivingSocial and other deal sites that sell something from the venues recommended. There are no ads and there’s no mobile app. Personally, I’m a fan of this approach but unless they get moving, they’re probably going to run out of cash to make this sustainable. Also doesn’t help that they don’t have a sales team.
Anyway, call it typecasting or excess homogenizing but Loku’s basic premise and rational rings true. When I go to Dupont Circle in DC, I’m looking for something upscale; when I go to Adams Morgan, I’m looking for something … downscale; and when I go to Columbia Heights/green line, I’m looking for indie. I’m not sure how I’d classify Arlington but maybe Loku will learn to parse YouTube videos.
