SociAL Sensor Analytics: Measuring phenomenology at scale

Abstract

The objective of this paper is to present a system for interrogating immense social media streams through analytical methodologies that characterize topics and events critical to tactical and strategic planning. First, we propose a conceptual framework for interpreting social media as a sensor network. Time-series models and topic clustering algorithms are used to implement this concept into a functioning analytical system. Next, we address two scientific challenges: 1) to understand, quantify, and baseline phenomenology of social media at scale, and 2) to develop analytical methodologies to detect and investigate events of interest. This paper then documents computational methods and reports experimental findings that address these challenges. Ultimately, the ability to process billions of social media posts per week over a period of years enables the identification of patterns and predictors of tactical and strategic concerns at an unprecedented rate through SociAL Sensor Analytics (SALSA).

Social sensor analytics: Making sense of network models in social media

“…Notable topics in June 2014 include the second largest cluster corresponding to threeletter country abbreviations used during the 2014 World Cup. Compared to our previous work [3], June 2014 is about half as large in terms of number of hashtags within the top 15 clusters; more research into minimum sample size is needed.…”

“…Time series modeling [1]- [3] typically seeks to detect and characterize patterns in data feature frequency. Graph-based modeling [4]- [9] often aims to capture network communities or describe how information is being propagated about the network and between communities.…”

“…Graph-based modeling [4]- [9] often aims to capture network communities or describe how information is being propagated about the network and between communities. A number of frameworks for analysis that combine these methods have been proposed [3], [6], [10]- [12]. This work does not introduce a new framework, but rather seeks to both build on and raise more questions about an apparent consensus-based on current research directions-within the research community that Twitter, among other forms of social media, is a sensor network mapping real world information onto the web.…”

“…[3] In our ongoing research, we wish to create models of forms of global information dissemination on this sensor network. Modeling such a network on a global network is an enormous challenge.…”

“…Using the cosine similarity as a distance semimetric, we identify related hashtags that in practice appear to be latent topical clusters. An in-depth analysis of hashtag clustering applied to approximately two years of Twitter data can be found in our previous work [3].…”