Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval
SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
Authoritative sources in a hyperlinked environment
Journal of the ACM (JACM)
Snowball: extracting relations from large plain-text collections
DL '00 Proceedings of the fifth ACM conference on Digital libraries
Small is beautiful: discovering the minimal set of unexpected patterns
Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
Learning to construct knowledge bases from the World Wide Web
Artificial Intelligence - Special issue on Intelligent internet systems
Discovering unexpected information from your competitors' web sites
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Proceedings of the 11th international conference on World Wide Web
Cumulated gain-based evaluation of IR techniques
ACM Transactions on Information Systems (TOIS)
Web-scale information extraction in knowitall: (preliminary results)
Proceedings of the 13th international conference on World Wide Web
Combating web spam with trustrank
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
Searching for Important But Neglected Content from Community-Type-Content
SITIS '08 Proceedings of the 2008 IEEE International Conference on Signal Image Technology and Internet Based Systems
Content hole search in community-type content
Proceedings of the 18th international conference on World wide web
A generalized Co-HITS algorithm and its application to bipartite graphs
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
A machine learning approach for improved BM25 retrieval
Proceedings of the 18th ACM conference on Information and knowledge management
Coupled semi-supervised learning for information extraction
Proceedings of the third ACM international conference on Web search and data mining
Hi-index | 0.00 |
Although many studies have addressed the problem of finding Web pages seeking relevant and popular information from a query, very few have focused on the discovery of unexpected information. This paper provides and evaluates methods for discovering unexpected information for a keyword query. For example, if the user inputs "Michael Jackson," our system first discovers the unexpected related term "karate" and then returns the unexpected information "Michael Jackson is good at karate." Discovering unexpected information is useful in many situations. For example, when a user is browsing a news article on the Web, unexpected information about a person associated with the article can pique the user's interest. If a user is sightseeing or driving, providing unexpected, additional information about a building or the region is also useful. Our approach collects terms related to a keyword query and evaluates the degree of unexpectedness of each related term for the query on the basis of (i) the relationships of coordinate terms of both the keyword query and related terms, and (ii) the degree of popularity of each related term. Experimental results show that considering these two factors are effective for discovering unexpected information.