Trending topics in microblogs such as Twitter are valuable resources to under-stand social aspects of real-world events. To enable deep analyses of such trends, se-mantic annotation is an effective approach; yet the problem of annotating microblog trending topics is largely unexplored by the research community. In this work, we tackle the problem of mapping trending Twitter topics to entities from Wikipedia. We propose a novel model that comple-ments traditional text-based approaches by rewarding entities that exhibit a high tem-poral correlation with topics during their burst time period. By exploiting temporal information from the Wikipedia edit his-tory and page view logs, we have improved the annotation performance by 17-28%, as compared to the competitive baselines. 1

Once every five minutes, Twitter publishes a list of trending topics by monitoring and analyzing tweets from its users. Similarly, Google makes available hourly a list of hot queries that have been issued to the search engine. We claim that social trends fired by Twitter may help explain and predict web trends derived from Google. Indeed, we argue that infor-mation flooding nearly real-time across the Twitter social network could anticipate the set of topics that users will later search on the Web. In this work, we analyze the time series derived from the daily volume index of each trend, either by Twitter or Google. Our study on a real-world dataset reveals that about 26 % of the trending topics raising from Twitter “as-is ” are also found as hot queries issued to Google. Also, we find that about 72 % of the similar trends appear first on Twitter. Thus, we assess the relation between comparable Twitter and Google trends by testing three classes of time series regression models. First, we find that Google by its own is not able to effectively predict the time behavior of its trends. In-deed, we show that autoregressive models, which try to fit time series of Google trends, perform poorly. On the other hand, we validate the forecasting power of Twitter by showing that models, which use Google as the dependent variable and Twitter as the explana-tory variable, retain as significant the past values of Twitter 60 % of times. Moreover, we discover that a Twitter trend causes a similar Google trend to later occur about 43 % of times. In the end, we show that the very best-performing models are those using past values of both Twitter and Google. I