Hashtags are used in Twitter to classify messages, propagate ideas and also to promote specific topics and people. In this paper, we present a linguistic-inspired study of how these tags are created, used and disseminated by the members of information networks. We study the propagation of hashtags in Twitter grounded on models for the analysis of the spread of linguistic innovations in speech communities, that is, in groups of people whose members linguistically influence each other. Differently from traditional linguistic studies, though, we consider the evolution of terms in a live and rapidly evolving stream of content, which can be analyzed in its entirety. In our experimental results, using a large collection crawled from Twitter, we were able to identify some interesting aspects – similar to those found in studies of (offline) speech – that led us to believe that hashtags may effectively serve as models for characterizing the propagation of linguistic forms, including: (1) the existence of a “preferential attachment process”, that makes the few most common terms ever more popular, and (2) the relationship between the length of a tag and its frequency of use. The understanding of formation patterns of successful hashtags in Twitter can be useful to increase the effectiveness of real-time streaming search algorithms. to the topic of the message. They can be used not only to add context and metadata to the posts, but also for promotion and publicity. By simply adding a hash symbol (#) before a string of letters, numerical digits or underscore signs (_), it is possible to tag a message, helping other users to find tweets that have a common topic. Hashtags allow users to create communities of people interested in the same topic by making it easier for them to find and share information related to it (Kricfalusi, 2009). Figure 1 shows an example of query for the tag “#basketball”, which returns the newest tweets with this hashtag. 1

Abstract—In social media settings where users send messages to one another, the issue of reciprocity naturally arises: does the communication between two users take place only in one direction, or is it reciprocated? In this paper we study the problem of reciprocity prediction: given the characteristics of two users, we wish to determine whether the communication between them is reciprocated or not. We approach this problem using decision trees and regression models to determine good indicators of reciprocity. We extract a network based on directed

The identification of popular and important topics discussed in social networks is crucial for a better understanding of societal concerns. It is also useful for users to stay on top of trends without having to sift through vast amounts of shared information. Trend detection methods introduced so far have not used the network topology and has thus not been able to distinguish viral topics from topics that are diffused mostly through the news media. To address this gap, we propose two novel structural trend definitions we call coordinated and uncoordinated trends that use friendship information to identify topics that are discussed among clustered and distributed users respectively. Our analyses and experiments show that structural trends are significantly different from traditional trends and provide new insights into the way people share information online. We also propose a sampling technique for structural trend detection and prove that the solution yields in a gain in efficiency and is within an acceptable error bound. Experiments performed on a Twitter data set of 41.7 million nodes and 417 million posts show that even with a sampling rate of 0.005, the average precision is 0.93 for coordinated trends and 1 for uncoordinated trends. 1.

We are interested in the problem of tracking broad topics such as “baseball ” and “fashion ” in continuous streams of short texts, exemplified by tweets from the microblogging service Twitter. The task is conceived as a language modeling problem where per-topic models are trained using hashtags in the tweet stream, which serve as proxies for topic labels. Simple perplexity-based classifiers are then applied to filter the tweet stream for topics of interest. Within this framework, we evaluate, both intrinsically and extrinsically, smoothing techniques for integrating “foreground ” models (to capture recency) and “background ” models (to combat sparsity), as well as different techniques for retaining history. Experiments show that unigram language models smoothed using a normalized extension of stupid backoff and a simple queue for history retention performs well on the task.

Current social media research mainly focuses on temporal trends of the information flow and on the topology of the social graph that facilitates the propagation of information. In this paper we study the effect of the content of the idea on the information propagation. We present an efficient hybrid approach based on a linear regression for predicting the spread of an idea in a given time frame. We show that a combination of content features with temporal and topological features minimizes prediction error. Our algorithm is evaluated on Twitter hashtags extracted from a dataset of more than 400 million tweets. We analyze the contribution and the limitations of the various feature types to the spread of information, demonstrating that content aspects can be used as strong predictors thus should not be disregarded. We also study the dependencies between global features such as graph topology and content features.

The worldwide span of the microblogging service Twitter gives an opportunity to make international comparisons of trending topics of interest, such as news stories. Previous international comparisons of news interests have tended to use surveys and may bypass topics not well covered in the mainstream media. This article uses 9 months of English tweets from the

Copyright is held by the author/owner(s). CHI’12, May 5–10, 2012, Austin, Texas, USA. ACM 978-1-4503-1016-1/12/05. In this paper we describe the preliminary results and future directions of a research in progress, which aims at assessing the hashtag effectiveness as a resource for sentiment analysis expressed on Twitter. The results so far support our hypothesis that hashtags may facilitate the detection and automatic tracking of online population sentiment about different events.

Abstract—With the success of online social networks and microblogs such as Facebook, Flickr and Twitter, the phenomenon of influence exerted by users of such platforms on other users, and how it propagates in the network, has recently attracted the interest of computer scientists, information technologists, and marketing specialists. One of the key problems in this area is the identification of influential users, by targeting whom certain desirable marketing outcomes can be achieved. In this article we take a data mining perspective and we discuss what (and how) can be learned from the available traces of past propagations. While doing this we provide a brief overview of some recent progresses in this area and discuss some open problems. By no means this article must be intended as an exhaustive survey: it is instead (admittedly) a rather biased and personal perspective of the author on the topic of influence propagation in social networks.

private and academic purposes. Re-publication of material from this volume requires permission by the copyright owners.

News articles are extremely time sensitive by nature. There is also intense competition among news items to propagate as widely as possible. Hence, the task of predicting the popularity of news items on the social web is both interesting and challenging. Prior research has dealt with predicting eventual online popularity based on early popularity. It is most desirable, however, to predict the popularity of items prior to their release, fostering the possibility of appropriate decision making to modify an article and the manner of its publication. In this paper, we construct a multi-dimensional feature space derived from properties of an article and evaluate the efficacy of these features to serve as predictors of online popularity. We examine both regression and classification algorithms and demonstrate that despite randomness in human behavior, it is possible to predict ranges of popularity on twitter with an overall 84 % accuracy. Our study also serves to illustrate the differences between traditionally prominent sources and those immensely popular on the social web. 1