reference.bib

% For data collection
@misc{weibo2021,
	annote = {[Accessed: 2021-12-30]},
	author = {{Sina Weibo}},
	title = {{Sina Weibo API Capabilities}},
	url = {http://open.weibo.com/wiki/%E5%BE%AE%E5%8D%9AAPI}, 
	year = {2021},
	note = "[Online; accessed: 2021-12-30]"
}

@misc{twitter2021,
	annote = {[Accessed: 2021-12-30]},
	author = {{Twitter}},
	title = {{Twitter Developer Platform Docs}},
	url = {https://developer.twitter.com/en/docs}, 
	year = {2021},
	note = "[Online; accessed: 2021-12-30]"
}

@article{haklay2008openstreetmap,
	author = {Haklay, Mordechai and Weber, Patrick},
	journal = {IEEE Pervasive computing},
	number = {4},
	pages = {12--18},
	publisher = {Ieee},
	title = {{Openstreetmap: User-generated street maps}},
	volume = {7},
	year = {2008}
}

% For Methodology

@Article{info9050102,
	AUTHOR = {Coşkun, Mustafa and Ozturan, Meltem},
	TITLE = {#europehappinessmap: A Framework for Multi-Lingual Sentiment Analysis via Social Media Big Data (A Twitter Case Study)},
	JOURNAL = {Information},
	VOLUME = {9},
	YEAR = {2018},
	NUMBER = {5},
	ARTICLE-NUMBER = {102},
	URL = {https://www.mdpi.com/2078-2489/9/5/102},
	ISSN = {2078-2489},
	ABSTRACT = {The growth and popularity of social media platforms have generated a new social interaction environment thus a new collaboration and communication network among individuals. These platforms own tremendous amount of data about users’ behaviors and sentiments since people create, share or exchange their information, ideas, pictures or video using them. One of these popular platforms is Twitter, which via its voluntary information sharing structure, provides researchers data potential of benefit for their studies. Based on Twitter data, in this study a multilingual sentiment detection framework is proposed to compute European Gross National Happiness (GNH). This framework consists of a novel data collection, filtering and sampling method, and a newly constructed multilingual sentiment detection algorithm for social media big data, and tested with nine European countries (United Kingdom, Germany, Sweden, Turkey, Portugal, The Netherlands, Italy, France and Spain) and their national languages over a six year period. The reliability of the data is checked with peak/troughs comparison for special days from Wikipedia news lists. The validity is checked with a group of correlation analyses with OECD Life Satisfaction survey reports’, Euro-Dollar and other currency exchanges, and national stock market time series data. After validity and reliability confirmations, the European GNH map is drawn for six years. The main problem addressed is to propose a novel multilingual social media sentiment analysis framework for calculating GNH for countries and change the way of OECD type organizations’ survey and interview methodology. Also, it is believed that this framework can serve more detailed results (e.g., daily or hourly sentiments of society in different languages).},
	DOI = {10.3390/info9050102}
}

@article{BAO2017358,
	title = {Incorporating twitter-based human activity information in spatial analysis of crashes in urban areas},
	journal = {Accident Analysis & Prevention},
	volume = {106},
	pages = {358-369},
	year = {2017},
	issn = {0001-4575},
	doi = {https://doi.org/10.1016/j.aap.2017.06.012},
	url = {https://www.sciencedirect.com/science/article/pii/S0001457517302269},
	author = {Jie Bao and Pan Liu and Hao Yu and Chengcheng Xu},
	keywords = {Big data, Human activity, Twitter, Safety, Spatial analysis},
	abstract = {The primary objective of this study was to investigate how to incorporate human activity information in spatial analysis of crashes in urban areas using Twitter check-in data. This study used the data collected from the City of Los Angeles in the United States to illustrate the procedure. The following five types of data were collected: crash data, human activity data, traditional traffic exposure variables, road network attributes and social-demographic data. A web crawler by Python was developed to collect the venue type information from the Twitter check-in data automatically. The human activities were classified into seven categories by the obtained venue types. The collected data were aggregated into 896 Traffic Analysis Zones (TAZ). Geographically weighted regression (GWR) models were developed to establish a relationship between the crash counts reported in a TAZ and various contributing factors. Comparative analyses were conducted to compare the performance of GWR models which considered traditional traffic exposure variables only, Twitter-based human activity variables only, and both traditional traffic exposure and Twitter-based human activity variables. The model specification results suggested that human activity variables significantly affected the crash counts in a TAZ. The results of comparative analyses suggested that the models which considered both traditional traffic exposure and human activity variables had the best goodness-of-fit in terms of the highest R2 and lowest AICc values. The finding seems to confirm the benefits of incorporating human activity information in spatial analysis of crashes using Twitter check-in data.}
}