Spatio-Temporal-Thematic Analysis of Citizen Sensor Data: Challenges and Experiences

Lecture notes in computer sciencePublished 1 January 2009Open access

Meenakshi Nagarajan, Karthik Gomadam, Amit Sheth, Ajith Ranabahu, Raghava Mutharaju, Ashutosh Jadhav

Citations97

TL;DR

Using Twitter as a platform for obtaining crowd-sourced observations, the interplay between the 3 dimensions in extracting insightful summaries of observations is explored, and the experiences in building a web mashup application that facilitates the spatio-temporal-thematic exploration of social signals underlying events are presented.

Abstract

We present work in the spatio-temporal-thematic analysis of citizen-sensor observations pertaining to real-world events. Using Twitter as a platform for obtaining crowd-sourced observations, we explore the interplay between these 3 dimensions in extracting insightful summaries of social perceptions behind events. We present our experiences in building a web mashup application, Twitris that extracts and facilitates the spatio-temporal-thematic exploration of event descriptor summaries.

Keywords

Computer ScienceSocial SciencesPhysics and Astronomy

Information Processing & ManagementTerm-weighting approaches in automatic text retrieval

9,532 Citations1988Gerard Salton, Chris Buckley

This paper summarizes the insights gained in automatic term weighting, and provides baseline single term indexing models with which other more elaborate content analysis procedures can be compared.

Word association norms, mutual information, and lexicography

1,066 Citations1989Kenneth Church, Patrick Hanks

The proposed measure, the association ratio, estimates word association norms directly from computer readable corpora, making it possible to estimate norms for tens of thousands of words.

View PDF

IEEE Intelligent SystemsMaking Sense of Sensemaking 1: Alternative Perspectives

780 Citations2006Gary Klein, B. Moon +1 more

This essay examines sensemaking from various perspectives to see if the authors can separate the things that are doable from the Things that seem more like pie-in-the-sky.

A study of retrospective and on-line event detection

731 Citations1998Yiming Yang, Tom Pierce +1 more

This paper applied hierarchical and non-hierarchical document clustering algorithms to a corpus of 15,836 stories, focusing on the exploitation of both content and temporal information, and found the resulting cluster hierarchies highly informative for retrospective detection of previously unidentified events.

Communications of the ACMExperiential computing

119 Citations2003Ramesh Jain

Seeking insight from data, users experience, explore, and experiment, no longer limited to just generating lists of possible answers to simplistic queries.

Temporal and information flow based event detection from social text streams

88 Citations2007Qiankun Zhao, Prasenjit Mitra +1 more

This paper proposes to detect events from social text streams by exploring the content as well as the temporal, and social dimensions by combining text based clustering, temporal segmentation, and information flow-based graph cuts of the dual graph of the social networks.

Fighter cockpits of the future

82 Citations2002Eugene C. Adam

This paper examines tactical cockpit problems needed to solve them and recommend three generations of solutions and what is the payoff.

arXiv (Cornell University)Extraction of Keyphrases from Text: Evaluation of Four Algorithms

62 Citations2002Peter D. Turney

An empirical evaluation of four algorithms for automatically extracting keywords and keyphrases from documents finds NRCs Extractor yields the best match with the manually generated keyphRases.

View PDF

A graph-theoretic approach to extract storylines from search results

54 Citations2004Ravi Kumar, Uma Mahadevan +1 more

A graph-theoretic approach to discover storylines from search results, based on generalizations of the maximum induced matching problem on bipartite graphs, which offers a concise organization of the wealth of information hidden beyond the first page of search results.

Growing Fields of Interest - Using an Expand and Reduce Strategy for Domain Model Extraction

17 Citations2008Christopher Thomas, Pankaj Mehra +2 more

Doozer, a program for building conceptual models of information domains, wants to bridge the gap between the vocabularies and Folksonomies on the one side and the rich, expert-designed ontologies and taxonomy on the other.