%0 Journal Article %1 Wang:2015:WUS:2788341.2746366 %A Wang, Yazhe %A Callan, Jamie %A Zheng, Baihua %C New York, NY, USA %D 2015 %I ACM %J ACM Trans. Web %K adaptiveCrawler streaming twitter %N 3 %P 13:1--13:23 %R 10.1145/2746366 %T Should We Use the Sample? Analyzing Datasets Sampled from Twitter&Rsquo;s Stream API %U http://doi.acm.org/10.1145/2746366 %V 9 %X Researchers have begun studying content obtained from microblogging services such as Twitter to address a variety of technological, social, and commercial research questions. The large number of Twitter users and even larger volume of tweets often make it impractical to collect and maintain a complete record of activity; therefore, most research and some commercial software applications rely on samples, often relatively small samples, of Twitter data. For the most part, sample sizes have been based on availability and practical considerations. Relatively little attention has been paid to how well these samples represent the underlying stream of Twitter data. To fill this gap, this article performs a comparative analysis on samples obtained from two of Twitter’s streaming APIs with a more complete Twitter dataset to gain an in-depth understanding of the nature of Twitter data samples and their potential for use in various data mining tasks.

@article{Wang:2015:WUS:2788341.2746366, abstract = {Researchers have begun studying content obtained from microblogging services such as Twitter to address a variety of technological, social, and commercial research questions. The large number of Twitter users and even larger volume of tweets often make it impractical to collect and maintain a complete record of activity; therefore, most research and some commercial software applications rely on samples, often relatively small samples, of Twitter data. For the most part, sample sizes have been based on availability and practical considerations. Relatively little attention has been paid to how well these samples represent the underlying stream of Twitter data. To fill this gap, this article performs a comparative analysis on samples obtained from two of Twitter’s streaming APIs with a more complete Twitter dataset to gain an in-depth understanding of the nature of Twitter data samples and their potential for use in various data mining tasks.}, acmid = {2746366}, added-at = {2016-08-15T11:09:23.000+0200}, address = {New York, NY, USA}, articleno = {13}, author = {Wang, Yazhe and Callan, Jamie and Zheng, Baihua}, biburl = {https://www.bibsonomy.org/bibtex/213c21699d8a8abedf9833c67402821f6/asmelash}, description = {Should We Use the Sample? Analyzing Datasets Sampled from Twitter’s Stream API}, doi = {10.1145/2746366}, interhash = {ea68dde86e53a1791278a1556b82a2b9}, intrahash = {13c21699d8a8abedf9833c67402821f6}, issn = {1559-1131}, issue_date = {June 2015}, journal = {ACM Trans. Web}, keywords = {adaptiveCrawler streaming twitter}, month = jun, number = 3, numpages = {23}, pages = {13:1--13:23}, publisher = {ACM}, timestamp = {2016-09-06T15:30:02.000+0200}, title = {Should We Use the Sample? Analyzing Datasets Sampled from Twitter\&Rsquo;s Stream API}, url = {http://doi.acm.org/10.1145/2746366}, volume = 9, year = 2015 }