Nowadays with the development of technology and access to the Internet everywhere for everyone, the interest to get the news from newspapers and other traditional media is decreasing. Therefore, the popularity of news websites is ascending as the newspapers are changing into electronic versions. News websites can be accessed from anywhere, i.e., any country, city, region, etc. So, the need to present the news depends on where the reader is from can be a research area, as with facing with variety of news topics on websites readers prefer to choose those which more often show the news, they are interested in on their home pages. Based on this idea we represent the technique to find favorite topics of Twitter users of certain geographical districts to provide news websites a way of increasing popularity. In this work we processed tweets. It seems that tweets are some small data, but we found out that processing this small data needs a lot of time, due to the repetition of the algorithm a lot and many searches to be done. Therefore, we categorized our work as big data. To help this problem we developed our work in the Spark framework. Our technique includes 2 phases; Feature Extraction Phase and Topic Discovery Phase. Our analysis shows that with this technique we can get the accuracy between 68% and 76%, in 3 developments 3-fold, 5-fold, and 10-fold.