Improvement of News Ranking through Importance Prediction
نویسندگان
چکیده
The use of Internet to search for information regarding a variety of topics of interest to users is still growing. The issue of how to manage and recommend that information is still an open area of research, namely concerning news recommendations. In this paper we use a recently developed approach to predict extreme and rare values of a variable to forecast the future importance of news items from Google News, using Twitter as proxy, in an attempt to improve the news rankings recommended by Google. Results using three different correlation metrics show that the obtained news rankings are more correlated with the users preferences than the rankings obtained with Google News.
منابع مشابه
A Framework for Exploration of News Corpora by Actor Evolution and Interaction
We present a general framework for modeling and exploration of news corpus. The natural way to model a news corpus is as a directed graph where stories are linked to one another through a variety of relationships. We formalize this notion by viewing each news story as a set of actors, and by viewing links between stories as transformations these actors go through. We propose and model a simple ...
متن کاملTop Stories Identification From Blog to News in TREC 2010 Blog Track
In 2010 Blog Track, there are two tasks including Faceted Blog Distillation Task and Top Stories Identification Task. We mainly focus on the Top Stories Identification Task. In this task, there are two issues to solve. The first issue is ranking the important news stories on the specified day, named Story Ranking Task. The second issue is named News Blog Post Ranking Task. News Blog Post Rankin...
متن کاملNews article ranking: leveraging the wisdom of bloggers
Every day, editors rank news articles for placement within their newspapers. In this paper, we investigate how news article ranking can be performed automatically. In particular, we investigate the blogosphere as a prime source of evidence, on the intuition that bloggers, and by extension their blog posts, can indicate interest in one news article or another. Moreover, we propose to model this ...
متن کاملRanking Effective Bases on Performance of Human Resource Planning Systems (Correlation and Fuzzy Approach)
EnThe present research studied the relationship between organizational learning elements and human resources performance. Population of the research consisted of all managers Tehran Telecommunication Company. Data were collected through questionnaires which included 24 questions with seven items. To determine the impact and ranking theprinciples of organizational learning in performance of huma...
متن کاملEigenvector Based Approach for Sentence Ranking in News Summarization
In this era of information overload, it is necessary to have a mechanism to identify and present the textual information effectively. There are lot of redundant information currently available in the Internet and news is one such domain which holds a major share. To handle redundant information, the first and foremost thing is to identify the similarity among the available content. All those si...
متن کامل