Why Google, Bing, Yahoo, and Other Search Engines Should Try the Semantic Web Technology?

Google redesigning of their “Google News” is not really the significant argument. Although, they should pay attention on how the news is relevant and how to engage the audience by better reach capabilities to retrieve the news by topic matter opposed to key words.

I think if Google change the way how you retrieve and interact with news is way more important than design. Needles to say, the way consumers search for news is changing the news industry as a whole. Google’s most recent purchase of Metaweb for a disclosed amount of $57 million is in the right direction to be more semantic than it is now.

I suggest for Google to rethink their design over, and while they are at it, they should also consider looking at new technology. A library for text processing that performs semantic analysis on (news like) textual documents. The API can be used to generate lucid document summarization, extractions of key topics, and most importantly, it can be used to index and retrieve documents by topic/subject matter as opposed to key words.

Taking another example similar to the subject with hand, a technology that process and analyze concepts, not words, and this includes names of things (people, countries, organizations, products, etc.). Thus, from words they try to infer the most likely meaning in context by a process known as Word Sense Disambiguation (WSD), which is an essential part of the semantic analysis process. The accuracy the technology’s WSD algorithm in inferring the most likely meaning of a word in some context is above 80%, and, as far as we know, this accuracy rate is by far much higher than any WSD results that have been reported in the computational linguistics research.

A technology that give words meanings, including names of things. To do so basic reference resolution and entity identification has to be performed. Names of people, organizations, movies, etc. are not therefore just words and phrases, but are full-fledged concepts that can be related to and matched with other concepts and topics. Thus, while the sentence “popularity of former NY Yankees slugger Babe Ruth” is not at all related to “Dr. Ruth popularity in NY”, there is clearly some semantic relation between “US President Barack Obama” and “German Chancellor Angela Merkel” (due, among other things, to the semantic relationship between ‘Barack Obama’ and ‘Chancellor’, for example).

In summary, Google have redesigned “Google News”, but they also should reconsider to design the way to retrieve news to be more semantic with better retrieval content. In this way, Google will avoid the strategic mistake of positioning content in key word search. Needless to say, if they consider to also introducing more semantic applications for better news service retrieval; this can’t hurt anyone. In this way, Google will be considered a semantic web rather than a search engine with key word/s based search engine.




Leave a Reply

Your email address will not be published.