Measuring public sentiment is a key task for researchers and policymakers alike. The explosion of available social media data allows for a more time-sensitive and geographically specific analysis than ever before. In this paper we analyze data from the micro-blogging site Twitter and generate a sentiment map of New York City. We develop a classifier specifically tuned for 140-character Twitter messages, or tweets, using key words, phrases and emoticons to determine the mood of each tweet. This method, combined with geotagging provided by users, enables us to gauge public sentiment on extremely fine-grained spatial and temporal scales. We find that public mood is generally highest in public parks and lowest at transportation hubs, and locate other areas of strong sentiment such as cemeteries, medical centers, a jail, and a sewage facility. Sentiment progressively improves with proximity to Times Square. Periodic patterns of sentiment fluctuate on both a daily and a weekly scale: more positive tweets are posted on weekends than on weekdays, with a daily peak in sentiment around midnight and a nadir between 9:00 a.m. and noon.

Online social media influence the flow of news and other information, potentially altering collective social action while generating a large volume of data useful to researchers. Mapping these networks may make it possible to predict the course of social and political movements, technology adoption, and economic behavior. Here, we map the network formed by Twitter users sharing British Broadcasting Corporation (BBC) articles. The global audience of the BBC is primarily organized by language with the largest linguistic groups receiving news in English, Spanish, Russian, and Arabic. Members of the network primarily “follow” members sharing articles in the same language, and these audiences are primarily located in geographical regions where the languages are native. The one exception to this rule is a cluster interested in Middle East news which includes both Arabic and English speakers. We further analyze English‐speaking users, which differentiate themselves into four clusters: one interested in sports, two interested in United Kingdom (UK) news—with word usage suggesting this reflects political polarization into Conservative and Labour party leanings—and a fourth group that is the English speaking part of the group interested in Middle East news. Unlike the previously studied New York Times news sharing network the largest scale structure of the BBC network does not include a densely connected group of globally interested and globally distributed users. The political polarization is similar to what was found for liberal and conservative groups in the New York Times study. The observation of a primary organization of the BBC audience around languages is consistent with the BBC's unique role in history as an alternative source of local news in regions outside the UK where high quality uncensored news was not available. © 2014 Wiley Periodicals, Inc. Complexity 19: 55–63, 2014