We present an overview of the CLEF-2019 Lab ProtestNews on Extracting Protests from News in the context of generalizable natural language processing. The lab consists of document, sentence, and token level information classification and extraction tasks that were referred as task 1, task 2, and task 3 respectively in the scope of this lab. The tasks required the participants to identify protest relevant information from English local news at one or more aforementioned levels in a cross-context setting, which is cross-country in the scope of this lab. The training and development data were collected from India and test data was collected from India and China. The lab attracted 58 teams to participate in the lab. 12 and 9 of these teams submitted results and working notes respectively. We have observed neural networks yield the best results and the performance drops significantly for majority of the submissions in the cross-country setting, which is China.

We propose a coherent set of tasks for protest information collection in the context of generalizable natural language processing. The tasks are news article classification, event sentence detection, and event extraction. Having tools for collecting event information from data produced in multiple countries enables comparative sociology and politics studies. We have annotated news articles in English from a source and a target country in order to be able to measure the performance of the tools developed using data from one country on data from a different country. Our preliminary experiments have shown that the performance of the tools developed using English texts from India drops to a level that are not usable when they are applied on English texts from China. We think our setting addresses the challenge of building generalizable NLP tools that perform well independent of the source of the text and will accelerate progress in line of developing generalizable NLP systems.

This paper puts forward four main arguments regarding the persistence of significant rural support of the Justice and Development Party (Adalet ve Kalkınma Partisi, AKP) in Turkey since late 2002. Firstly, since the previous coalition government implemented the harshest neoliberal measures in the agricultural sector, small farmers do not directly associate neoliberal assault with the AKP administration. Secondly, villagers have utilized both the ballot box and direct action in order to bargain with the AKP. Thirdly, although the AKP government did not fundamentally depart from neoliberalism, the return of agricultural subsidies, significant expansion of social assistance, and rapid infrastructure construction have secured a large rural following for the party. Finally, the AKP government has effectively used coercive methods to prevent the emergence of an emancipatory political alternative.

Agrarian structures based on small peasant property can have two opposite kinds of impact on urban wages. In the first type, stable smallholder farming bringing high returns puts upward pressure on wages. In the second type, smallholder farming that does not bring sufficient returns leads to semi-proletarianization in which workers' access to rural sources of income functions as wage subsidy and puts downward pressure on wages.This paper argues that the situation in Turkey between 1950 and 1980 fits the second type. By pointing out the factors that changed the attitude of the migrant labourers towards class struggle from relative passivity to increasing militancy, it suggests that instead of the rural ties of the emerging working class, the main reason behind the dramatic rise in urban wages in Turkey in the 1960s and 1970s was the working-class struggle throughout the period.

We describe a gold standard corpus of protest events that comprise various local and international English language sources from various countries. The corpus contains document-, sentence-, and token-level annotations. This corpus facilitates creating machine learning models that automatically classify news articles and extract protest event-related information, constructing knowledge bases that enable comparative social and political science studies. For each news source, the annotation starts with random samples of news articles and continues with samples drawn using active learning. Each batch of samples is annotated by two social and political scientists, adjudicated by an annotation supervisor, and improved by identifying annotation errors semi-automatically. We found that the corpus possesses the variety and quality that are necessary to develop and benchmark text classification and event extraction systems in a cross-context setting, contributing to the generalizability and robustness of automated text processing systems. This corpus and the reported results will establish a common foundation in automated protest event collection studies, which is currently lacking in the literature.