Using sentiment analysis with Big Data tools to enrich knowledge on society in the city
AbstractUsing Big Data in terms of providing valuable information for city authorities is usually related to the machine generated data, mostly coming from various sensors installed on different parts of the cities. One of the most common example is a road sensor. It can be used to plan the roads building in the city. However, the valuable data can also be provi ded from continuing analysis of human generated data, provided by people on different communication channels used by the city authorities. It includes social media portals and self -government websites in which people can create content, such as comments. T he aim of this research is to show the value added for the city authorities by making sentiment analysis on various social media and comments on websites. These types of communication is very often a subject of analysis for enterprises to perform the market recognition of customers, but there is still lack of using these methods by city authorities. The goal of this paper is to show a case study of using different Web 2.0 and 3.0 communication forms to build a common view of city inhabitants related to diff erent aspects of the city. For this case study, a proposal framework has been developed and illustrated, using different types of text mining methods to make sentiment analysis. The results from the study show that Big Data may have a big impact on support ing the development of the city. The proposal of the framework presented in this paper is ready to be applied in a production process and serve for the city. The threats and opportunities have been identified and future work has also been presented.
|Journal series||Smart Cities and Regional Development Journal, ISSN 2537-3803, (0 pkt)|
|Publication size in sheets||0.50|
|Keywords in English||Big Data, sentiment analysis, decision making, text mining, web mining|
|Score||= 5.0, 28-01-2020, ArticleFromJournal|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.