Analysis of Forest Landscape Preferences and Emotional Features of Chinese Forest Recreationists Based on Deep Learning of Geotagged Photos

Forest landscape preference studies have an important role and significance for forest conservation, quality improvement utilization. However, there are few on objective preferences from the perspective of plants using photos. This study relies Deep Learning technology to select six case sites in China uses geotagged photos landscapes posted by recreationists “2BULU” app as research objects. The eight scenes, including look down landscape, forward up single-tree-composed detailed overall trail intra-forest were explored. It also Deepsentibank perform sentiment analysis better understand Chinese recreationists’ preferences. results show that: (1) From aesthetic spatial angle, people prefer flat view, while attention elevated view is relatively low. (2) scale level, has a high preference, implying that plays recreation. within certain individual, (3) Although photographs extremely positive emotions emotional states, negative emotions, thus, illustrating people’s can be both negative.