classecol: Classifiers to understand public opinions of nature

Abstract

Methods in Ecology and Evolution This article has been accepted for publication and undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as

Understanding Landscape Aesthetics Using a Novel Viewshed Assessment of Social Media Locations Within the Troodos UNESCO Global Geopark, Cyprus

“…While this "word association" approach offers a simple and transparent method for assessing textual sentiment, the choice of dictionary can influence results and the polarity of sentences. To solve these well-known issues, the "classecol" R package (Johnson et al, 2021) applies 11 different dictionaries to a piece of text to better calculate the expressed sentiment. Furthermore, the sophisticated model of polarity better captures the complexities of expressed sentiment by assessing and accounting for the valence of the text including negators ("e.g., "I am not happy"), amplifiers (e.g., "I am very happy"), de-amplifiers (e.g., "I am not that happy"), and adversative conjunction terms (e.g., "I am happy, but sad").…”

“…Social media datasets may therefore need classifying to better represent these positive interactions between people and nature, with previous studies filtering posts based on the content of images (Gosal et al, 2019;Zhao and Han, 2021), or sentiment expressed in textual metadata (Fox et al, 2021a). Here, we address sentiment in terms of where the social media post reflects a positive attitude towards nature (Johnson et al, 2021).…”

Ecosystem Services: A Social and Semantic Network Analysis of Public Opinion on Twitter

“…Most authors, however, have focused exclusively on cultural ecosystem services by mapping and quantifying them using images [ 31 , 32 , 33 , 34 ], and few of them have analysed their social perceptions [ 15 , 35 , 36 ]. With reference to Twitter, several authors have analysed the social perception of natural capital, that is, nature and its ecosystem services and protected areas [ 37 , 38 , 39 ] or people’s emotions [ 40 ], but few have focused exclusively on ecosystem services and specifically cultural services [ 41 , 42 , 43 , 44 ]. The only study that analysed the perception of ecosystem services in a broad sense focused on a specific geographical area, namely the Laurentian Great Lakes [ 45 ].…”

“…Based on the empirical evidence found in the literature [ 38 , 39 ], the topic under research and our theories, the respective hypotheses for the research questions were identified: (H1) In the social network, there are good interactions between users and high content sharing. (H2) Most influential users in the network are scientists or researchers.…”

Automated synthesis of biodiversity knowledge requires better tools and standardised research output

“…Within the medical literature, some approaches have even managed to automate the entire systematic review procedure (Marshall and Wallace 2019, Gates et al 2020, Marshall et al 2020, Yang et al 2020, Brassey et al 2021). In the environmental sciences, automated topic models have provided insight into research trends (Hintzen et al 2020) and the identification of knowledge gaps (Westgate et al 2015), with text-classifiers allowing for the automated analysis of social media content to understand public opinions of nature (Johnson et al 2021a). Complementing these broader, summarisation approaches, direct extraction of ecologically valuable information from literature (e.g.…”