摘要：Thanksgiving and Christmas are two major holidays in the United States. Many people use social media to stay connected with their families and friends, including sharing their holiday experiences. This study utilized a stream of millions of tweets on Twitter to explore how people feel about these two holidays through real-time sentiment analysis. With help of Twitter Streaming API, we discovered the patterns of sentiment changes by hour before and after the two holidays in 2011, thus providing a unique peek into the celebration of these holidays that could not be accomplished with traditional methods. Our analysis suggested that in 2011 people had higher sentiment toward Christmas than Thanksgiving on average. The sentiment reached its maximum on the Thanksgiving Day and on The Christmas Eve and Christmas Day, highlighting stronger zeal for Christmas than Thanksgiving, while remained a stable and lower sentiment before and after the holidays. Typically there was a peak of sentiment toward Thanksgiving and Christmas in the morning of each day around 9:00am (EST). On the Thanksgiving Day the number of tweets on shopping increased rapidly and monotonically to its maximum as time approaching the midnight when people thinking of shopping on the Black Friday, but unexpectedly the sentiment toward shopping dropped quickly and monotonically, displaying the exact opposite trend. We also investigated the shopping distraction on the theme of these two holidays. It was found that there were more people talking about thankfulness than shopping during the Thanksgiving season, but more people talking about shopping than Jesus during the Christmas season.
关键词：Twitter; Thanksgiving; Christmas; Sentiment Analysis; Streaming API
