Directed links in social media could represent anything from intimate friendships to common interests, or even a passion for breaking news or celebrity gossip. Such directed links determine the flow of information and hence indicate a user’s influence on others—a concept that is crucial in sociology and viral marketing. In this paper, using a large amount of data collected from Twitter, we present an in-depth comparison of three measures of influence: indegree, retweets, and mentions. Based on these measures, we investigate the dynamics of user influence across topics and time. We make several interesting observations. First, popular users who have high indegree are not necessarily influential in terms of spawning retweets or mentions. Second, most influential users can hold significant influence over a variety of topics. Third, influence is not gained spontaneously or accidentally, but through concerted effort such as limiting tweets to a single topic. We believe that these findings provide new insights for viral marketing and suggest that topological measures such as indegree alone reveals very little about the influence of a user.

Analyzing user messages in social media can measure different population characteristics, including public health measures. For example, recent work has correlated Twitter messages with influenza rates in the United States; but this has largely been the extent of mining Twitter for public health. In this work, we consider a broader range of public health applications for Twitter. We apply the recently introduced Ailment Topic Aspect Model to over one and a half million health related tweets and discover mentions of over a dozen ailments, including allergies, obesity and insomnia. We introduce extensions to incorporate prior knowledge into this model and apply it to several tasks: tracking illnesses over times (syndromic surveillance), measuring behavioral risk factors, localizing illnesses by geographic region, and analyzing symptoms and medication usage. We show quantitative correlations with public health data and qualitative evaluations of model output. Our results suggest that Twitter has broad applicability for public health research.

Web search is strongly influenced by time. The queries people issue change over time, with some queries occasionally spiking in popularity (e.g., earthquake) and others remaining relatively constant (e.g., youtube). Likewise, the documents indexed by a search engine change, with some documents always being about a particular query (e.g., the Wikipedia page on earthquakes is about the query earthquake) and others being about the query only at a particular point in time (e.g., the New York Times is only about earthquakes following a major seismic activity). The relationship between documents and queries can also change as people’s intent changes (e.g., people sought different content for the query earthquake before the Haitian earthquake than they did after). In this paper, we explore how queries, their associated documents, and the query intent change over the course of 10 weeks by analyzing query log data, a daily Web crawl, and periodic human relevance judgments. We identify several interesting features by which changes to query popularity can be classified, and show that presence of these features, when accompanied by changes in result content, can be a good indicator of change in query intent.

Rapid response to a health epidemic is critical to reduce loss of life. Existing methods mostly rely on expensive surveys of hospitals across the country, typically with lag times of one to two weeks for influenza reporting, and even longer for less common diseases. In response, there have been several recently proposed solutions to estimate a population’s health from Internet activity, most notably Google’s Flu Trends service, which correlates search term frequency with influenza statistics reported by the Centers for Disease Control and Prevention (CDC). In this paper, we analyze messages posted on the micro-blogging site Twitter.com to determine if a similar correlation can be uncovered. We propose several methods to identify influenza-related messages and compare a number of regression models to correlate these messages with CDC statistics. Using over 500,000 messages spanning 10 weeks, we find that our best model achieves a correlation of.78 with CDC statistics by leveraging a document classifier to identify relevant messages.

Analysis of Google Influenza-like-illness (ILI) search queries has shown a strongly correlated pattern with Center for Disease Control and Prevention seasonal ILI reporting data. Web and social media (WSM) provide another resource to detect increases in ILI. This paper evaluates trends in blog posts that discuss Influenza. The results of the analysis show Influenza-related blogging trends have a significant correlation with the beginning of US Fall 2008 flu season. We also identify WSM Influenza-related communities that share flu-postings which could broker or disseminate information in the case of a severe outbreak or Influenza epidemic.

Recent work has shown that search query volume correlates well with a variety of phenomena, from influenza caseloads to economic indicators like real-estate prices, auto sales, and travel statistics. In this paper, we investigate the degree to which search behavior predicts the commercial success of cultural products, namely movies, video games, and songs. In contrast with previous work that has focused on realtime reporting of current trends, we emphasize that here our objective is to predict future activity, typically days to weeks in advance. Specifically, we use query volume to forecast opening weekend box-office revenue for feature films, first month sales of video games, and the rank of songs on the Billboard Hot 100 chart. In all cases that we consider, we find that search counts are indicative of future outcomes, but when compared with baseline models trained on publicly available data, the performance boost associated with search counts is generally modest—a pattern that, as we show, also applies to previous work on tracking flu trends. We conclude that in the absence of other data sources, or where small improvements in predictive performance are material, search queries may provide a useful guide to the near future.

Users on Twitter, a microblogging service, started the phenomenon of adding tags to their messages sometime around February 2008. These tags are distinct from those in other Web 2.0 systems because users are less likely to index messages for later retrieval. We compare tagging patterns in Twitter with those in Delicious to show that tagging behavior in Twitter is different because of its conversational, rather than organizational nature. We use a mixed method of statistical analysis and an interpretive approach to study the phenomenon. We find that tagging in Twitter is more about filtering and directing content so that it appears in certain streams. The most illustrative example of how tagging in Twitter differs is the phenomenon of the Twitter micro-meme: emergent topics for which a tag is created, used widely for a few days, then disappears. We describe the micro-meme phenomenon and discuss the importance of this new tagging practice for the larger real-time search context.

An important question in behavioral epidemiology and public health is to understand how individual behavior is affected by illness and stress. Although changes in individual behavior are intertwined with contagion, epidemiologists today do not have sensing or modeling tools to quantitatively measure its effects in real-world conditions. In this paper, we propose a novel application of ubiquitous computing. We use mobile phone based co-location and communication sensing to measure characteristic behavior changes in symptomatic individuals, reflected in their total communication, interactions with respect to time of day (e.g., late night, early morning), diversity and entropy of face-to-face interactions and movement. Using these extracted mobile features, it is possible to predict the health status of an individual, without having actual health measurements from the subject. Finally, we estimate the temporal information flux and implied causality between physical symptoms, behavior and mental health.

Abstract. Internet search engines have become an increasingly popular resource for accessing health-related information. The key words used as well as the number and geographic location of searches can provide trend data, as have recently been made available by Google Trends. We report briefly on exploring this resource using Lyme disease as an example because it has well-described seasonal and geographic patterns. We found that search traffic for the string “Lyme disease ” reflected increased likelihood of exposure during spring and summer months; conversely, the string “cough ” had higher relative traffic during winter months. The cities and states with the highest amount of search traffic for “Lyme disease ” overlapped considerably with those where Lyme is known to be endemic. Despite limitations to over-interpretation, we found Google Trends to approximate certain trends previously identified in the epidemiology of Lyme disease. The generation of this type of data may have valuable future implications in aiding surveillance of a broad range of diseases.

Text and structural data mining of web and social media (WSM) provides a novel disease surveillance resource and can identify online communities for targeted public health communications (PHC) to assure wide dissemination of pertinent information. WSM that mention influenza are harvested over a 24-week period, 5 October 2008 to 21 March 2009. Link analysis reveals communities for targeted PHC. Text mining is shown to identify trends in flu posts that correlate to real-world influenza-like illness patient report data. We also bring to bear a graph-based data mining technique to detect anomalies among flu blogs connected by publisher type, links, and user-tags.