![]() |
![]() |
GI_Forum 2018, Volume 6, Issue 1Journal for Geographic Information Science
|
![]() |
Verlag der Österreichischen Akademie der Wissenschaften Austrian Academy of Sciences Press
A-1011 Wien, Dr. Ignaz Seipel-Platz 2
Tel. +43-1-515 81/DW 3420, Fax +43-1-515 81/DW 3400 https://verlag.oeaw.ac.at, e-mail: verlag@oeaw.ac.at |
![]() |
|
DATUM, UNTERSCHRIFT / DATE, SIGNATURE
BANK AUSTRIA CREDITANSTALT, WIEN (IBAN AT04 1100 0006 2280 0100, BIC BKAUATWW), DEUTSCHE BANK MÜNCHEN (IBAN DE16 7007 0024 0238 8270 00, BIC DEUTDEDBMUC)
|
GI_Forum 2018, Volume 6, Issue 1, pp. 47-64, 2018/06/22
Journal for Geographic Information Science
The Arctic, and with it the State of Alaska, USA, is an area highly impacted by climate change. Changing environmental conditions have started to impact local communities, causing a need for changes ranging from new infrastructure to the relocation of entire towns. These changes connected to rising temperatures have been shown to affect people’s overall health, and their mental health in particular. Previous studies using opinion-mining and Twitter data have focused on large areas, not distinguishing between regions within countries. In the course of the research presented in this paper, we analysed Twitter data for the period 2013–2017, from which we extracted opinions concerning climate change topics by applying sentiment analysis (polarity and feelings) and climate change dictionaries, on a 10 x 10 km grid for the State of Alaska, USA. The number of climate change-relevant tweets was found to be much lower than reported in previous studies, where the USA was only considered in its entirety. After applying a topic-modelling approach, we found little difference between the spatial distributions of hotspots for the different climate change topics. A comparison with population data showed considerable biases towards English-speaking communities, tweets in indigenous languages being excluded when pre-defined dictionaries in English were used.
Keywords: Social Media, Climate Change, Alaska, opinion mining