A Proposed Upgrade to the Keyword Based Searches Essay

Decent Essays
INTRODUCTION: KEYWORD-BASED search has been the most popular search in today’s searching world. The result of Keyword based search is better than Google .On Google search engine user or searcher did not find relevant image result. This is because of two reasons. Queries are in general short and non-specific. Number of users may have different intentions for the same query . Searching for apple by a farmer has a different meaning from searching by a technical person .There is one solution to solve these problems is personalized search where user specific information is considered to distinguish between exact intentions of user queries and reranked the images. Figure.1: (top) non-personalized and (bottom) personalized…show more content…
User Specific Topic Modeling (USTM) 3. Topic-Sensitive Users Preferences (TSUP) Online stage: 4. User Specific Query Mapping (USQM) 5. Ranking Based Image Searching. 1. Ranking Based Multicorrelation tensor Factorization (RMTF): When user u tagged on any particular image id, then that user id, image id, tag named is stored into a database at an offline stage. This database is in the format of ternary interrelationship between users, images and tags. This database is give as an input to RMTF model. The RMTF model calculates user’s preferences to assign the tag to a particular image i.e. RMTF provide the users annotation prediction. The tagging data can be viewed as a set of triplets (U×I×T).RMTF calculates users preferences by using sigmoid(objective) function Sigmoid function retunes values between 0 to 1 that means user preferences lies in between 0 to 1. 2. User Specific Topic Modeling (USTM): After calculating RMTF values, corpus is created for generating topic modeling. Corpus is the folder in which no of folders are created for each user manually. Each folder contains text file for each image and that text file contains tags that user given to that particular image. Corpus is gives as an input to the algorithm.LDA algorithm performed topic modeling. USTM model gives topics for each user; each topic has specific number of relevant terms to each other. 3. Topic-Sensitive
Get Access