News aggregators gather thousands of news articles every day from across the world and cluster them into news stories comprising large numbers of articles about the same event. This is even augmented by the increasing amount of information in social media (e.g., Twitter, Facebook) where mass opinions about news events can be monitored. A promising way to reduce this bulk of highly redundant data is offered by the language technologies known as multi-document text summarisation and sentiment analysis. A major problem is that news articles are in many languages while current technology has mostly dealt with English, and the question of how current research can be applied in a heavily multilingual context has barely been addressed. Most multi-document summarisation research has focused on the news domain and MediaGist will do likewise in order to build on existing techniques and resources. However, summarising posts in social media, representing complementary and unbiased information, will be considered as well. Media professionals, however, will want to go beyond summaries from sources in one language and consider how news events are reported in other countries and from other perspectives. Identifying differences in opinion towards entities and events may provide some clues as the disagreements in reporting across languages. MediaGist will perform multilingual sentiment analysis and will thus make possible the generation of summaries that reveal these disagreements. The goal of MediaGist is to make significant advances in multilingual research so as to extract and present the GIST (the main content and opinions) of online multilingual news and the corresponding content in social media.