Multi-lingual Analysis of Future-Related Information on the Web.

Future prediction is one of the crucial activities of humans. In this paper, we report the results of exploratory analysis of future-related information on the Web in three different languages: English, Japanese and Polish. We focus on the future-related information which is grounded in time, that is, the information on events whose expected occurrence dates are already known. Our datasets are constructed by crawling search engine indices. We investigate multiple aspects of future-related information in web pages across different languages such as its amount, time span, topics, associated sentiment levels as well as the relation to the future-related content in news articles.