Automatic keyword extraction from a real estate classifieds data set

In this age where information and internet technologies are developing at a radical pace, users have the access to large amount of documents and information online. With the increasing amount of information, it also becomes an area of interest on how to make online search easier. Keywords are consid...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Devassy, Dibin (author)
منشور في: 2011
الموضوعات:
الوصول للمادة أونلاين:http://bspace.buid.ac.ae/handle/1234/76
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:In this age where information and internet technologies are developing at a radical pace, users have the access to large amount of documents and information online. With the increasing amount of information, it also becomes an area of interest on how to make online search easier. Keywords are considered to be a solution to this problem and are now widely used to search the information over the internet.In this project we analyze a real estate classifieds data set, with an objective to find keywords that represent this data set. We begin with designing data cleansing algorithms to verify different attributes of the real estate classified. Further, we progress to extract the candidate keywords from the cleansed data set. Finally, we develop a method to automatically extract the keywords and also the key phrases that are formed along with the keywords.