Home / Monitoring Imooty. Fresh posts., Online Reputation Monitoring, market intelligence, media intelligence, media monitoring, online reputation management, social media monitoring / Named entity recognition: Paris Hilton, or the Hotel in Paris?
-->
Named entity recognition: Paris Hilton, or the Hotel in Paris?
If you’re the PR or Marketing lead in any of the two operations, this question is a real pain. Every day, its your job to be sorting out the mentions that could potentially have something to do with your organization; Is the agitated forum discussion about that last Paris Hilton gig, or the Hilton Hotel in Paris? It is menial, annoying and very costly as it relies on brute manpower to get through it all.
So, when monitoring the Hilton Hotel in Paris, Imooty uses advanced text recognition to eliminate the Paris Hilton mentions from the search results. But how do we do that? Initially, we feed the software with selected articles that clearly are about the Hilton Hotel in Paris and Paris Hilton, the artist. Having learned what the two categories look like, the software can start to automatically separate them from one-another.
Named entity recognition, pretty cool tool, is what that is.
The sheer amount of social media data to go through is what makes this problem a real issue. People now share common interest and experiences with like minded strangers and the total amount of digital information in the world double 2 times EVERY DAY!
- Paris Hilton, recognized as a named entity via Wikipedia
What used to be called Public Relations, has become Community Management. Gone are the days of one-to-many communication (mass media) when getting a message out there was to get a journalist interested enough to consider doing a story. Social media on the other hand, is a one-to-one-to-many format and to keep track, you need more than a fancy way of counting online mentions.
The future is in analytical applications that educate users about things they don’t already know. It’s about gaining knowledge of the unknown, combining the data of the past with strategic solutions that help you move forward. Together with Yukka GmbH, Imooty offers interpretation of large data pools by way of computer linguistic tools.
Do you already use a monitoring tool and are looking for a smarter way to process information? Try our free media monitoring trial or drop us a line at info@imooty.eu.
Sounds fantastic, I know a few people at Orange Mobile who will jump at this!
What happens if a post falls in both categories, for example “Paris Hilton visits Paris, booked in at the Hilton”?
There’s a feedback function so that the user can correct misplaced articles. This way the software can continually develop and improve.
For certain ontologies we can also determine the likelihood that an article belongs in one category or the other. For example, the above headline is really about Paris Hilton and her stay in the French capital and the software can assign a 60% probability that it belongs in the celebrity category.
Can this be used for topical information too? News topic Sports, Finance, Politics etc.? Also, what’s the pricing, has it anything to do with your standard product offer? http://www.imooty.eu/product.php
The tool works best within specific contexts. If the topic is too general, like the news categories you mention, there will be overlap and difficulty in creating a category with specific properties. Financial news is for example frequently peppered by political decision making, and financial institutions frequently sponsor sport events.
As for pricing, this is an analytical tool and not included in our monitoring price model you refer to. It is determined on a case-by-case basis, i.e. how much effort do we have to put into the machine learning process.