<![CDATA[The number of movie production have increased each year. This shows that the society interest in the film industry is getting higher. It's difficult to get the appropriate result of what desired by searching for data with certain parameters on the internet because of the large amount of data exists but there is limited adequate tools. The screening of the excess data can be done using recommendation process. There are several stages in movie recommendation process. Those are Pre-processing to process film synopsis documents, TF-IDF method to obtain the highest value as much as the amount determined based on the query result on the document. Word2vec as a method to get the query expansion from the top word result that taken from TF-IDF process and Cosine Similarity is used to get the similarity between document and query. The Word2Vec method plays role to find the proximity value between words to one another in order to get the words that will be added to the initial query. The training data are 150 movies title with English synopsis. The evaluation process took 30 data of movie title and synopsis from the training data based on the movies selected by the examiners. The highest Precision@k value is 0,47 and the highest Mean Average Precision (MAP) value is 0.709603374.]]>
Copyrights © 2019
