Extracting knowledge from the web and social media for progress monitoring in public outreach and science communication

Published 5 November 2013

Arno Scharl, David Herring

Citations4

TL;DR

The NOAA Media Watch is introduced and a detailed case study how the metrics and visualizations of the webLyzard Web intelligence platform are used to track information flows across online media channels is presented.

Abstract

Given the intense attention that environmental topics such as climate change attract in news and social media coverage, key questions for large science agencies such as the National Oceanic and Atmospheric Administration (NOAA) are how different stakeholders perceive the observable threats and policy options, how public media react to new scientific insights, and how journalists present climate science knowledge to the public. This paper investigates the potential of semantic technologies to address these questions. It introduces the NOAA Media Watch and presents a detailed case study how the metrics and visualizations of the webLyzard Web intelligence platform are used to track information flows across online media channels. Building upon this platform, we present a novel framework to measure the impact of science communication and public outreach campaigns -- through a combination of quantitative and visual methods that go beyond sentiment analysis and related opinion mining approaches.

Keywords

Computer Science

IEEE Transactions on Visualization and Computer GraphicsD³ Data-Driven Documents

3,153 Citations2011M. G. Bostock, V. Ogievetsky +1 more

This work shows how representational transparency improves expressiveness and better integrates with developer tools than prior approaches, while offering comparable notational efficiency and retaining powerful declarative components.

Information diffusion through blogspace

1,045 Citations2004Daniel Gruhl, R. Guha +2 more

A macroscopic characterization of topic propagation through the authors' corpus is presented, formalizing the notion of long-running "chatter" topics consisting recursively of "spike" topics generated by outside world events, or more rarely, by resonances within the community.

ACM SIGKDD Explorations NewsletterInformation diffusion through blogspace

951 Citations2004Daniel Gruhl, David Liben‐Nowell +2 more

A macroscopic characterization of topic propagation through the authors' corpus, formalizing the notion of long-running "chatter" topics consisting recursively of "spike" topics generated by outside world events, or more rarely, by resonances within the community.

IEEE Internet ComputingThe Future of Social Networks on the Internet: The Need for Semantics

238 Citations2007John G. Breslin, Stefan Decker

This paper argues that the semantic Web is a useful platform for linking and for performing operations on diverse person-and object-related data gathered from heterogeneous social networking sites, and that object-centered networks can serve as rich data sources for semantic Web applications.

IEEE Intelligent SystemsExtracting and Grounding Contextualized Sentiment Lexicons

103 Citations2013Albert Weichselbraun, Stefan Gindl +1 more

A context-aware approach based on machine learning and lexical analysis identifies ambiguous terms and stores them in contextualized sentiment lexicons, which ground the terms to concepts corresponding to their polarity.

Information SciencesMultiple coordinated views for searching and navigating Web content repositories

40 Citations2009Alexander Hubmann-Haidvogel, Arno Scharl +1 more

The implementation of multiple coordinated views within the Media Watch on Climate Change, a domain-specific news aggregation portal available at www.ecoresearch.net/climate that combines a portfolio of semantic services with a visual information exploration and retrieval interface is described.

Cadernos de Linguística e Teoria da Literatura (Universidade Federal de Minas Gerais)A Context-Dependent Supervised Learning Approach to Sentiment Detection in Large Textual Databases

34 Citations2010Albert Weichselbraun, Stefan Gindl +1 more

A novel method that uses Naive Bayes to identify ambiguous terms and a contextualized sentiment lexicon that stores the polarity of these terms, together with a set of co-occurring context terms is introduced.

Media Watch on Climate Change -- Visual Analytics for Aggregating and Managing Environmental Knowledge from Online Sources

18 Citations2013Arno Scharl, Alexander Hubmann-Haidvogel +3 more

The Media Watch on Climate Change is presented, a public Web portal that captures and aggregates large archives of digital content from multiple stakeholder groups that assesses the domain-specific relevance of millions of documents and user comments from news media, blogs, Web 2.0 platforms, and a range of other sources.

Document Clustering Using Semantic Kernels Based on Term-Term Correlations

9 Citations2009Ahmed Farahat, Mohamed S. Kamel

This paper analyzes semantic kernels that are based on term-term correlations that capture different aspects of correlations between terms, and shows that the proposed method achieves significant improvement in document clustering compared to VSM.

International Journal of Metadata Semantics and OntologiesTracking and modelling information diffusion across interactive online media

6 Citations2007Arno Scharl, Albert Weichselbraun +1 more

The IDIOM research project analyses this process of information diffusion by identifying redundant content elements, mapping them to ontology concepts, and tracking their temporal and geographic distribution.