Introduction to the special section on twitter and microblogging services

Welcome to this special section on Twitter and Microblogging Services, which features five articles on different aspects of microblogging and related topics. We are putting forward this special section because, in recent years, we have witnessed a dramatic increase in the amount of research done on Twitter and other microblogging services, and we believe that a special journal section on this topic is timely and will serve our community well. The special section comes out with high-quality selected articles that were originally presented in various top international conferences. These articles have been expanded and extended with more detailed contents from the authors to ensure a deeper understanding of their respective work. A brief introduction of the five articles follows. A Content-Driven Framework for Geolocating Microblog Users by Zhiyuan Cheng, James Caverlee, and Kyumin Lee investigates the use of a probabilistic framework for estimating a microblogger’s location based on the content of the microblog. The framework has to overcome the geodata sparsity problem and is capable of estimating the user’s location within a radius. The second article is Named Entity Recognition for Tweets by Xiaohua Liu, Furu Wei, Shaodian Zhang, and Ming Zhou. Named Entity Recognition (NER) is an active and challenging research topic in microblogging due to insufficient content and lack of training data. This article proposes a combination of machine learning techniques to tackle this problem with good and effective results. In the third article, Improving Recency Ranking Using Twitter Data, Yi Chang, Anlei Dong, Pranam Kolari, Ruiqiang Zhang, Yoshiyuki Inagaki, Fernando Diaz, Hongyuan Zha, and Yan Liu examine the use of Recency ranking, which incorporates relevancy and freshness in overcoming the lack of in-links and click information issue. Their approach utilizes Twitter TinyURL to detect fresh and high-quality tweets for generating ranking. Lexical Normalization for Social Media Text by Bo Han, Paul Cook, and Timothy Baldwin targets out-of-vocabulary words in tweets in order to tackle word noise in brief messages. Based on morphophonemic similarity, their approach detects lexical variants in order to generate the correct candidates for correcting words. The final article is Reorder User’s Tweets by Keyi Shen, Jianmin Wu, Ya Zhang, Yiping Han, Xiaokang Yang, Li Song, and Xiao Gu. Typically microblogs are displayed in a reversed chronological order. This article proposes a supervised learning method for personalized tweens reordering based on users’ preferences and interests by minimizing the pairwise loss of relevant and irrelevant tweets. The guest editors would like to thank all the authors and the reviewers for their contributions to this special section. Special thanks go to Weike Pan and Xiaofeng Yu for their administrative assistances. Finally, we would like to thank ACM TIST and