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.