Identification of Landscape Preferences by Using Social Media Analysis

People attribute different values to landscapes. These values are due to people's preferences, which are shaped by aesthetics, recreational benefits, safety, and other features of landscapes. Classic methods for studying landscape preferences include surveys and questionnaires, where study participants score or evaluate photos. Since almost 70% of US adults use social media to connect with friends and families, or to follow news and topics of interest (Pew research, 2015), research is needed to identify whether social media postings provide useful information about preferences for landscape settings. In this paper, we label text comments from Flickr, Instagram, and Twitter to train a lexicon-based sentiment classification model for predicting people's sentiments about green infrastructures, which are a specific landscape element. The results show a 77% correlation between text based sentiments from social media and image based landscape preferences.

[1]  Baoxin Li,et al.  Unsupervised Sentiment Analysis for Social Media Images , 2015, IJCAI.

[2]  Efstathios Stamatatos,et al.  Words versus Character n-Grams for Anti-Spam Filtering , 2007, Int. J. Artif. Intell. Tools.

[3]  Yücel Saygin,et al.  Learning Domain-Specific Polarity Lexicons , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[4]  Megha Agrawal,et al.  Predicting Individual Well-Being Through the Language of Social Media , 2016, PSB.

[5]  Erik Cambria,et al.  SenticNet 2: A Semantic and Affective Resource for Opinion Mining and Sentiment Analysis , 2012, FLAIRS.

[6]  A. Guerry,et al.  Using social media to quantify nature-based tourism and recreation , 2013, Scientific Reports.

[7]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[8]  F. Conrad,et al.  Social Media Analyses for Social Measurement. , 2016, Public opinion quarterly.

[9]  Uzay Kaymak,et al.  Exploiting emoticons in sentiment analysis , 2013, SAC '13.

[10]  M. Thelwall,et al.  Data mining emotion in social network communication: Gender differences in MySpace , 2010 .

[11]  William C. Sullivan,et al.  Perceptions of the rural-urban fringe: citizen preferences for natural and developed settings , 1994 .

[12]  Yücel Saygin,et al.  Sentiment Analysis Using Domain-Adaptation and Sentence-Based Analysis , 2015, Advances in Social Media Analysis.

[13]  David R. Thomas,et al.  A General Inductive Approach for Analyzing Qualitative Evaluation Data , 2006 .

[14]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[15]  M. McHugh.  Interrater reliability: the kappa statistic , 2012, Biochemia medica.

[16]  Lu Zhang,et al.  Become a Fan : A Conceptual Model for Social Media Marketing , 2010 .

[17]  Nitesh V. Chawla,et al.  Data Mining for Imbalanced Datasets: An Overview , 2005, The Data Mining and Knowledge Discovery Handbook.

[18]  G. Bormetti.  Option Pricing under Ornstein-uhlenbeck Stochastic Volatility Received (day Month Year) Revised (day Month Year) , 2002 .