Land Use Identification through Social Network Interaction

The Internet generates large volumes of data at a high rate, in particular, posts on social networks. Although network have numerous semantic adulterations and are not intended to be source geo-spatial information, the text we find pieces important information about how people relate their environment, which can used identify interesting aspects human beings interact with portions land based activities. This research proposes methodology for identification uses using Natural Language Processing (NLP) from contents popular Twitter. It will approached by identifying keywords linguistic patterns text, geographical coordinates associated publication. Context-specific innovations introduced deal across South America and, city Arequipa, Peru. objective is five main uses: residential, commercial, institutional-governmental, industrial-offices unbuilt land. Within framework urban planning sustainable management, contributes optimization techniques applied updating use cadastres, since results achieved an accuracy 90%, motivates its application real context. In addition, it would allow categories more detailed level, situations such as complex/mixed distribution building amount collected. Finally, makes available up-to-date fashion above all, avoids economic cost non-automatic production maps cities, mostly developing countries.