CCS'15 Poster: Network Analysis and Text Mining to characterize socio­cultural networks: Moorland management and self-­governance

We won a Best Poster Award at CCS'15 with this work!

Our work explores the integration of different computational techniques consisting of text mining and network analysis procedures. With these tools, we characterize the environmental resource management and governance actors in a Colombian moorland.
We develop a comprehensive methodology for describing the topology of the perceived interactions among stakeholders and characterizing them with the content of their discourses about moorland conservation. On one side, with this methodology we obtained:
* The networks or “ego-centered networks” based on the stakeholders or actors interviews.
* A complete network by merging ego-centered networks.
* Synergistic/antagonistic perceptions towards actors were represented in weighted networks.
* The identification of leaders among the interviewees.
On the other, interviews were analyzed with text mining, providing social and semantic context about the moorland conservation discourses. We finally integrated both approaches into a single framework.
Results illustrate the social structure of the moorland's leaders, their cultural context and their perceptions about the importance of the moorland ecosystem. On this basis, decision and policy-making for institutional and stakeholder actors could be improved. Moreover, the studied social system could be described in terms for guided self-organization.