Daily Corruption: News Feed & Database is a response to the deficiencies commonly pointed out against traditional aggregate indexes, on the one hand, and to the constraints regularly affecting case studies, on the other. Its objective is to provide daily, readily processed, and immediately available qualitative data on a number of characteristics concerning ongoing corruption cases, such as public sector affected (commerce, education, tax administration, etc.), specific type (bribery, embezzlement, money laundering, etc.), range (local, national, international), resources (petty, grand) and organizations involved (executive, judiciary, military, etc.), and several others. Furthermore, this data can then be automatically employed for statistical analysis, thus providing a new quantitative instrument to complement current instruments such as Transparency International’s Corruption Perception Index.
Hence, by being based on the daily input of data logs regarding corruption and anti-corruption events as communicated by the main media outlets of each country covered, the project aims to (1) limit the loss of data accuracy regarding the perception of political corruption; (2) drastically cut down the financial and logistic costs of conducting case studies in developing countries; (3) offer a constantly updated map of political corruption at the national level; and, perhaps most importantly, (4) provide an instrument for the follow-up of political will for anti-corruption efforts in each country.
The data is initially inputted manually by local partners of each participating country (the beta stage focusing on the Americas before rolling out to other regions), until enough information is available to train text classification algorithms and automatize about 70% of the process. In this way, the employment of text mining and natural language processing will provide long term sustainability to the project, while the participation of local experts and international organisations (such as Global Integrity) as separate levels of validation will make sure that the quality of the data remains at a proper level.
PLEASE VISIT http://dailycorruption.info/ TO KNOW MORE OR GET INVOLVED