No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
The Conflict and Peace Data Bank Project
Abstract
As students of politics and political science, we should and we do care about the events which lead to war, instability, and international tension as well as about events which lead to equitable interdependence, integration, peace, improvement of quality of life, reduction of colonialism, and so on. Because we care about these matters, we try to advance procedures and theories about systematizing our observations and improving our skills of analysis. Recent developments in international relations have tended to (a) emphasize the exploration of more specific problems and testing of hypotheses with quantified data and (b) deemphasized the search for general theories of internation behavior. This trend appears to be undergoing slight modification for many reasons. Events contain useful information which permit a student of foreign policy to use events singularly or in the aggregate to study foreign policy outputs and inputs. A student of international systems uses events singularly or in the aggregate to study patterns, structures, and transformation. This research calls for continuously developing models and operational procedures which analyze these phenomena with faster and better numerical precision. The Conflict and Peace Data Bank Project is the contribution of myself, my students, and my colleagues to this effort.
... WEIS 1 project [30]. Subsequently, other ontologies emerged, most notably, the COPDAB 2 [31], MID 3 [32], IDEA 4 [21], ACE 5 [33], CAMEO 6 [34], TAC 7 KBP [35], ICEWS 8 [36] and PLOVER 9 [37]. Among these, one of the most popular EOs is ACE, which has been employed to a large extent by many researchers since 2004 [38][39][40][41]. ...
... "Event arguments" are entities that fill specific roles in the corresponding event trigger [42]. The general roles are time (when), location (where), source (who: the initiator of the event), target (whom: the recipient of the event) and instruments )how: with what methods( [30,31]. Also, there are many other specific roles in event ontologies such as sentence, artifact etc. ...
... During the twentieth century, two event ontologies COPDAB 12 [31] developed by Edward Azar and Charles McClelland's WEIS [45] dominated event data research. These two EOs have focused on international politics, especially official diplomacy and military threats. ...
Data is published on the web over time in great volumes, but majority of the data is unstructured, making it hard to understand and difficult to interpret. Information Extraction (IE) methods extract structured information from unstructured data. One of the challenging IE tasks is Event Extraction (EE) which seeks to derive information about specific incidents and their actors from the text. EE is useful in many domains such as building a knowledge base, information retrieval, summarization and online monitoring systems. In the past decades, some event ontologies like ACE, CAMEO and ICEWS were developed to define event forms, actors and dimensions of events observed in the text. These event ontologies still have some shortcomings such as covering only a few topics like political events, having inflexible structure in defining argument roles, lack of analytical dimensions, and complexity in choosing event sub-types. To address these concerns, we propose an event ontology, namely COfEE, that incorporates both expert domain knowledge, previous ontologies and a data-driven approach for identifying events from text. COfEE consists of two hierarchy levels (event types and event sub-types) that include new categories relating to environmental issues, cyberspace, criminal activity and natural disasters which need to be monitored instantly. Also, dynamic roles according to each event sub-type are defined to capture various dimensions of events. In a follow-up experiment, the proposed ontology is evaluated on Wikipedia events, and it is shown to be general and comprehensive. Moreover, in order to facilitate the preparation of gold-standard data for event extraction, a language-independent online tool is presented based on COfEE.
... It is well argued that conflict/cooperation in transboundary water management is an important part of international politics, thus delicate or multi-level classification of sentiments is required. Most previous studies with manual coding methods adopted from 3 up to 15 levels (Azar 1980;Yoffe and Larson 2001;Grünwald et al. 2020b). Secondly, conflict/cooperation in transboundary water management requires not only an understanding of historical sentiment patterns on conflict and cooperation dynamics (Turton 2005;Zeitoun and Mirumachi 2008;Wei et al. 2021) but also the capability for timely monitoring and prediction of public sentiment surrounding such water conflicts (Warner 2023). ...
... Considering the dual requirements of classification and data characteristics, the number of labels was determined to be 5 in this study. Building on the characteristics of news media articles in this study and previous studies on defining the intensity of conflict or cooperation in transboundary water events (Azar 1980;Yoffe and Larson 2001;Grünwald et al. 2020b), the public sentiment polarities reflected Fig. 1 The flowchart of the methods in this study A comparative study of machine learning models for sentiment analysis of transboundary rivers news… in news media articles were categorized into five classes, corresponding to Cooperative response for actions (2), Oral expression of cooperative response (1), Neutrality (0), Oral expression of conflictive response (-1) and Conflictive response for actions (-2). Cooperative response for actions (2) signifies substantive collaborative actions in various fields jointly taken by the public or officials to achieve cooperation on water management, such as meetings, signing cooperation agreements/treaties, etc. ...
Sentiment analysis of news media articles is essential for understanding the dynamics of conflict and cooperation in transboundary rivers. However, it is not known which machine learning model(s) can best meet the requirement of sentiment analysis for transboundary rivers. This study presents a comparative examination of ten machine learning models commonly used in the field of text sentiment analysis, including K-Nearest Neighbors, Naive Bayes, Support Vector Machine, Decision Tree, Random Forest, Gradient Boosting Decision Tree, Extreme Gradient Boosting, Multilayer Perceptron, Long Short-Term Memory and Bidirectional Encoder Representations from Transformers, for five-class sentiment classification of 9382 news articles (1977–2022) attending to transboundary water conflict and cooperation. By evaluating their performance in terms of accuracy, precision, recall and F1-score, the Bidirectional Encoder Representations from Transformers (BERT) model demonstrated good overall performance and prediction capabilities for news articles with conflictive sentiments. By comparing with the AFINN sentiment dictionary, BERT showed superior performance in the prediction and identification of conflictive sentiment labels. And by validating against historical water events in the three river basins, BERT performed best in the Indus River basin. The findings of this study hold significant implications for government agencies in transboundary rivers, allowing them to promptly assess and respond to public sentiment, thereby preventing water conflict and promoting water cooperation.
... This is particularly true for unstructured, full-text event descriptions (Lepuschitz and Stoehr, 2021). As a consequence, there is a strong demand to parse, standardize and aggregate individual events into meaningful "conflict intensity" measures (Moses et al., 1967;Azar, 1980;McClelland, 1984). Today more than ever, quantitative measures of conflict intensity are indispensable for assessment of international relations, provision of humanitarian aid and political decision-making (Beck et al., 2000). ...
... Most work measures conflict intensity either by counting events (O'Connor et al., 2013;Schein et al., 2015) or fatalities (Kalyvas, 2006;Chaudoin et al., 2017). The Vincent (Vincent, 1979), COPDAB (Azar, 1980) and Goldstein Scale all rely on domain experts assigning abstract intensity scores to event types. scales on observed ordinal data. ...
For the quantitative monitoring of international relations, political events are extracted from the news and parsed into "who-did-what-to-whom" patterns. This has resulted in large data collections which require aggregate statistics for analysis. The Goldstein Scale is an expert-based measure that ranks individual events on a one-dimensional scale from conflictual to cooperative. However, the scale disregards fatality counts as well as perpetrator and victim types involved in an event. This information is typically considered in qualitative conflict assessment. To address this limitation, we propose a probabilistic generative model over the full subject-predicate-quantifier-object tuples associated with an event. We treat conflict intensity as an interpretable, ordinal latent variable that correlates conflictual event types with high fatality counts. Taking a Bayesian approach, we learn a conflict intensity scale from data and find the optimal number of intensity classes. We evaluate the model by imputing missing data. Our scale proves to be more informative than the original Goldstein Scale in autoregressive forecasting and when compared with global online attention towards armed conflicts.
... In practice, some previous researchers have proposed intensity scales to rank transboundary cooperative water events 1 . The first scale to measure the international conflict or cooperation intensity between nations was the 15-point COPDAB Scale introduced by Azar (1980b) [61]: point 1 represents the most cooperative event, and point 15 represents the most conflictive one [62]. However, the most renowned scale is the BAR Scale 2 , which was developed in the Basin at Risk (BAR) project of Oregon State University to evaluate the intensity of conflict or cooperative events occurring in the period 1948 to 1999 [63]. ...
... N. P. Lan on interactions between states, involving both conflict and cooperative interactions, that can contribute to the study of cooperation over international river basins, either directly or indirectly. In addition to the Conflict and Peace Data Bank (COPDAB) 1948-1978 [61], there are some other datasets, for example, Global Event Data System introduced by the Global Database of Events, Language, and Tone (GDELT) project and Environment and Security Water Conflict Chronology developed by Gleick (1993) [112]. However, while many of those datasets mainly focus on diplomatic and military interactions between countries, none specifically pay attention to water interactions in transboundary river basins. ...
... However, most of the existing quantitative literature that uses event data to analyze the interactions between the three countries is focused on the Cold War period. Manually coded event datasets of the Conflict and Peace Data Bank (COPDAB), available from 1948 to 1978 (Azar, 1980), and the World Events Interaction Survey (WEIS), available from 1966 to the 1990s (Azar, 1980), were mostly used to quantitatively study the superpower relations, as well as the relationships between politics and trade during the Cold War period. For instance, Ward (1982), Dixon (1986), McGinnis and Williams (1989), and Goldstein (1991) utilized COPDAB and WEIS event data to explore USA-Soviet relations during the Cold War period quantitatively. ...
... However, most of the existing quantitative literature that uses event data to analyze the interactions between the three countries is focused on the Cold War period. Manually coded event datasets of the Conflict and Peace Data Bank (COPDAB), available from 1948 to 1978 (Azar, 1980), and the World Events Interaction Survey (WEIS), available from 1966 to the 1990s (Azar, 1980), were mostly used to quantitatively study the superpower relations, as well as the relationships between politics and trade during the Cold War period. For instance, Ward (1982), Dixon (1986), McGinnis and Williams (1989), and Goldstein (1991) utilized COPDAB and WEIS event data to explore USA-Soviet relations during the Cold War period quantitatively. ...
The United States, Russia and China are militarily and economically among the most powerful countries in the post-Cold War period, and the interactions between the three powers heavily influence the international system. However, different conclusions about this question are generally made by researchers through qualitative analysis, and it is necessary to objectively and quantitatively investigate their interactions. Monthly-aggregated event data from the Global Data on Events, Location and Tone (GDELT) to measure cooperative and conflictual interactions between the three powers, and the complementary cumulative distribution function (CCDF) and the vector autoregression (VAR) method are utilized to investigate their interactions in two periods: January, 1991 to September, 2001, and October, 2001 to December, 2016. The results of frequencies and strengths analysis showed that: the frequencies and strengths of USA-China interactions slightly exceeded those of USA-Russia interactions and became the dominant interactions in the second period. Although that cooperation prevailed in the three dyads in two periods, the conflictual interactions between the USA and Russia tended to be more intense in the second period, mainly related to the strategic contradiction between the USA and Russia, especially in Georgia, Ukraine and Syria. The results of CCDF indicated that similar probabilities in the cooperative behaviors between the three dyads, but the differences in the probabilities of conflictual behaviors in the USA-Russia dyad showed complicated characteristic, and those between Russia and China indicated that Russia had been consistently giving China a hard time in both periods when dealing with conflict. The USA was always an essential factor in affecting the interactions between Russia and China in both periods, but China’s behavior only played a limited role in influencing the interactions between the USA-Russia dyad. Our study provides quantitative insight into the direct cooperative and conflictual interactions between the three dyads since the end of the Cold War and helps to understand their interactions better.
... Creating event datasets, where the unit of observation is typically one actor performing an action directed towards another actor, has been an active area of research since at least the 1970s and continues to constitute a fruitful research program at the forefront of many methodological developments (Azar, 1980, Boschee et al., 2015, Croicu and Weidmann, 2015, Halterman et al., 2017. The use of text, often from newspapers, dominates these efforts. ...
... The earliest method, and perhaps still the most common, uses humans to extract data from text. The Conflict and Peace Databank (COPDAB) is the first large-scale project of which we are aware that codes events across countries (Azar, 1980). The World Event/Interaction Survey (WEIS) is the other large event dataset from this era (McClelland, 1984). ...
While it is understood that protester identity, violence, and emotions affect the size of protests, these concepts have proved difficult to measure at the protest-day level. Geolocated text and images from social media can improve these measurements. This advance is demonstrated on protests in Venezuela and Chile; it uncovers more protests in Venezuela and generates new measures in both countries. Moreover, the methodology generates daily city-day protest data in 107 countries containing 82.7% of the world’s population and 97.15% of its GDP. These multimodal protest event data complement existing event datasets, though countries’ population and income constrain the reach of any methodology.
... Events are collected from newspapers like Reuters and automatically coded by a computer program. Conflict and Peace Databank (COPDAB) is another early dataset that includes events that occurred between 1948 and 1978 (Azar 1980). Event data research received significant funding from governmental agencies to provide information for policymakers. ...
Computational methods have been increasingly used in Foreign Policy Analysis (FPA). Text analysis, geospatial analysis, and network analysis are among the most used computational methods. This article examines the FPA literature that utilizes computational methods and discusses their theoretical and empirical implications for future research. I argue that while these methods are not without their criticisms, the integration of computational tools enables FPA researchers to create and use big data sets, improve sampling, and collect and analyze data. Computational methods in FPA enable theory-driven analysis of big data, providing both theoretical and empirical insights, and allowing testing of micro-level foundations of FPA theories. However, challenges such as the validity of measures and selection bias should be taken into account. While computational methods present significant opportunities for advancing FPA, these challenges need consideration.
... Many researchers have been compiling global datasets of various aspects of political conflict and adding substantive knowledge to trends in shared waterways. Most datasets evaluate conflict more broadly, not specifically related to water; these include Azar's Conflict and Peace Data Bank (COPDAB) (Azar, 1980); Uppsala Conflict Data Program Georeferenced Events Database (1946e2023); Penn State's Correlates of War (Correlated of War, 2022); Armed Conflict Location & Event Data (ACLED, 2024); as well as emerging datasets using machine learning, such as the GDELT Project (GDELT Project, 2022). Sources dedicated to water resources and hydropolitics have been emerging, such as the International Events Database (TFDD, 2024), New Events Dataset (Kalbhenn and Bernauer, 2012;Bernauer and Böhmelt, 2014), as well as the Water Conflict Chronology (Pacific Institute, 2023). ...
... In their simplest form, event data convert natural language reports to a dataset where each entry has the form of Date, Source Actor, Target Actor, Event Code [12]. Historically, many researchers conducted their studies using human-coded data, such as The Conflict and Peace Data Bank (COPDAB), which is a longitudinal computer-based library of daily international and domestic events or interactions [13] and WEIS Project dataset -which is a record of the flow of action and response between countries reflected in public facts [14]. However, these methods relied on costly human coding efforts that, after decades of research, came to an end [15]. ...
Embedding news articles is a crucial tool for multiple fields, such as media bias detection, identifying fake news, and news recommendations. However, existing news embedding methods are not optimized for capturing the latent context of news events. In many cases, news embedding methods rely on full-textual information and neglect the importance of time-relevant embedding generation. Here, we aim to address these shortcomings by presenting a novel lightweight method that optimizes news embedding generation by focusing on the entities and themes mentioned in the articles and their historical connections to specific events. We suggest a method composed of three stages. First, we process and extract the events, entities, and themes for the given news articles. Second, we generate periodic time embeddings for themes and entities by training timely separated GloVe models on current and historical data. Lastly, we concatenate the news embeddings generated by two distinct approaches: Smooth Inverse Frequency (SIF) for article-level vectors and Siamese Neural Networks for embeddings with nuanced event-related information. To test and evaluate our method, we leveraged over 850,000 news articles and 1,000,000 events from the GDELT project. For validation purposes, we conducted a comparative analysis of different news embedding generation methods, applying them twice to a shared event detection task - first on articles published within the same day and subsequently on those published within the same month. Our experiments show that our method significantly improves the Precision-Recall (PR) AUC across all tasks and datasets. Specifically, we observed an average PR AUC improvement of 2.15% and 2.57% compared to SIF, as well as 2.57% and 2.43% compared to the semi-supervised approach for daily and monthly shared event detection tasks, respectively.
... As discussed above, however, I argue that cooperation and conflict are quite often multilateral in nature. 2) In the French challenge to the U.S. foreign currency exchange system, the initial conflictual signal from France stimulated an American response that impacted relations with many states, not merely relations with For these analyses, I utilize two different data sets to generate my measures of conflict and cooperation: the Conflict and Peace Data Bank (COPDAB) (Azar 1982;1984) and the World Events Interaction Survey (WEIS) (McClelland 1978). Both data sets are the most frequently used sources of event count data for the study of interstate cooperation. ...
... Historically political event data have been made by hand (Azar, 1980;McClelland, 2006), by rulesbased software tools (Schrodt, 1998(Schrodt, , 2001(Schrodt, , 2011Schrodt et al., 2014;Norris et al., 2017), and via machine learning. Rules based software typically relies on large hand-curated dictionaries to perform pattern matching. ...
... NLP approaches have long played an important part in conflict research, as some of the first uses of NLP in conflict research were for the purpose of improving data collection efforts. Building on early work for collecting political event data by McClelland (1971) (WEIS) and Azar (1980) (COPDAB), researchers developed dictionaries and rule-based systems to automatically extract events from news articles. The Kansas Event Data System is one such pioneering attempt (Schrodt 2008). ...
Recent advancements in natural language processing (NLP) methods have significantly improved their performance. However, more complex NLP models are more difficult to interpret and computationally expensive. Therefore, we propose an approach to dictionary creation that carefully balances the trade-off between complexity and interpretability. This approach combines a deep neural network architecture with techniques to improve model explainability to automatically build a domain-specific dictionary. As an illustrative use case of our approach, we create an objective dictionary that can infer conflict intensity from text data. We train the neural networks on a corpus of conflict reports and match them with conflict event data. This corpus consists of over 14,000 expert-written International Crisis Group (ICG) CrisisWatch reports between 2003 and 2021. Sensitivity analysis is used to extract the weighted words from the neural network to build the dictionary. In order to evaluate our approach, we compare our results to state-of-the-art deep learning language models, text-scaling methods, as well as standard, nonspecialized, and conflict event dictionary approaches. We are able to show that our approach outperforms other approaches while retaining interpretability.
... Event extraction is a handy tool to monitor events automatically, such as detecting news events (Mitamura et al., 2017;Walker et al., 2006) and detecting international conflicts (Azar, 1980;Trappl, 2006). To foster research on event extraction, there are tremendous efforts into textual data collection (McClelland, 1976;Merritt et al., 1993;Raleigh et al., 2010;Schrodt & Hall, 2006;Sundberg & Melander, 2013), event coding schemes to accommodate different political events (Bond et al., 1997;Gerner et al., 2002;Goldstein, 1992), and dataset validity assessment (Schrodt & Gerner, 1994). ...
Language is the medium for many political activities, from campaigns to news reports. Natural language processing (NLP) uses computational tools to parse text into key information that is needed for policymaking. In this chapter, we introduce common methods of NLP, including text classification, topic modelling, event extraction, and text scaling. We then overview how these methods can be used for policymaking through four major applications including data collection for evidence-based policymaking, interpretation of political decisions, policy communication, and investigation of policy effects. Finally, we highlight some potential limitations and ethical concerns when using NLP for policymaking.
... The Conflict and Peace Data Bank (COPDAB) database of Azar (1980), which is the most established and widely used method, uses news articles reported in the media among 135 events that took place in countries, international organizations, and non-governmental organizations from 1948 to 1978. COPDAB collects and classifies news reports from multiple media sources into 15 types of events: one neutral event, seven positive events (cooperation) and seven negative events (dispute) (Reuveny and Kang 1996). ...
The recent advent of the New Cold War and rapid changes in global situation are increasing the need for quick and accurate geopolitical risk measurement through quantitative analysis. This study intends to present a new military-security index, a method of measuring military-geopolitical risk using big data analysis. In this regard, South Korea, one of the countries with the highest level of geopolitical risk in the world, was analyzed and quantified by analyzing direct provocations and threats from neighboring countries. The data used include the results of quantifying provocation cases in neighboring countries according to time, frequency, and intensity, the results of analyzing news keywords related to military-security issues in neighboring countries, and real-time terrorism and cybersecurity-risk measurements. Based on this, a model that enables relatively accurate and timely analysis and prediction by indexing and time-series geopolitical risks is presented.
... Indeed, most of the databases reviewed in the next sections use the same common framework to code event data (typically used for events that merit news coverage, and generally applied to the study of political news and violence) called Conflict and Mediation Event Observations (CAMEO). 99 Other alternative codebook exist, like the World Event/Interaction Survey (WEIS) coding system (Goldstein, 1992;McClelland, 2006) and the Conflict and Peace Data Bank (COPDAB) coding system (Azar, 2009). Here a brief summary of the available on-line resources is presented although how data is generated is not explained in full detail. ...
With the consolidation of the culture of evidence-based policymaking, the availability of data has become central to policymakers. Nowadays, innovative data sources offer an opportunity to describe demographic, mobility, and migratory phenomena more accurately by making available large volumes of real-time and spatially detailed data. At the same time, however, data innovation has led to new challenges (ethics, privacy, data governance models, data quality) for citizens, statistical offices, policymakers and the private sector. Focusing on the fields of demography, mobility, and migration studies, the aim of this report is to assess the current state of data innovation in the scientific literature as well as to identify areas in which data innovation has the most concrete potential for policymaking. Consequently, this study has reviewed more than 300 articles and scientific reports, as well as numerous tools, that employed non-traditional data sources to measure vital population events (mortality, fertility), migration and human mobility, and the population change and population distribution. The specific findings of our report form the basis of a discussion on a) how innovative data is used compared to traditional data sources; b) domains in which innovative data have the greatest potential to contribute to policymaking; c) the prospects of innovative data transition towards systematically contributing to official statistics and policymaking.
... PEA largely grew out of strike statistics, published since the early 20th century by government agencies in numerous countries, and including data on work stoppages, numbers of disputes and workers involved, and length of strikes. Hansen (1921) Azar 1980). Important studies, driven at heart by PEA, include those examining cycles of community protest (Tarrow 1989), the spread of race-based protest (Spilerman 1970), the role of official responses and repression (Khawaja 1994;Earl, Soule and McCarthy 2003), and innovations in movement organisation (Soule 2009). ...
A long-important tool for quantitative analysis of protests, the potential power of Protest Event Analysis (PEA) has only increased with the rise of Machine Learning technologies and the ubiquity of big data. PEA coders also present an advantage over contemporary Natural Language Programming innovations by being customisable to incorporate locally appropriate terms and vernaculars, expressed as personalised ontologies. As such, there is a need to develop a standard process for deploying machine learning tools that can draw on the local. This paper introduces such a tool, innovating the numeration of abstract indicators. “Machine Learning Protest Event Analysis Keyword Enumerated Recoding” is a protocol that enables PEA coders to read and classify large “event databases”, incorporating local terms and abstract indicators into the analysis. Applying this protocol to 150,000 records in a police-recorded database of crowd events in South Africa, protest events could be individually rated by levels of “tumult”—a feat hitherto inhibited by conventional PEA methods. Innovations in estimating crowd sizes, as well as an updated view of post-apartheid protest, showing that protests tend to be more common but less prone to violence than previous theories concluded, speaks to the potential for this protocol to unearth novel insights on even bigger data sets.
... Our research design is based on large-n machine-coded event data. Event data studies, which began with hand-coded projects such as the Conflict and Peace Data Bank (COPDAB) (Azar 1980) and the World Event/Interaction Survey Codebook (WEIS) (McClelland 1976) in the late 70s, faced important criticism initially due to a fundamental theoretical cleavage between scholars aiming at rich, detailed, and predictive analyses of specific cases and those aiming at a grand unified theory through conceptual and large-n studies (Hudson and Vore 1995). Event data studies fell under the latter. ...
Interactions between the EU and IGOs ˗ such as joint statements, verbal public disagreements, formal cooperation agreements, and IGO dispute resolution involving the EU ˗ have increased in the past decades. We address the question What determines the EU’s interactions with formal IGOs? by carrying out a big data-based sentiment analysis of all news published online between 1999 and 2017. Using over 30,000 events machine-coded by the Global Data Event Language and Tone (GDELT) database, we construct an annual measure for the dyadic relations between the EU and 36 formal IGOs. We find that when the EU has observer or member status in an IGO, this significantly and positively affects the quantity of interactions, while increasing the level of conflict in these interactions. Policy overlap between the EU and the IGO also increases the level of conflict in their interactions. Surprisingly, IGO authority is not relevant for these interactions.
... Until now, no work has been aimed at using Hong Kong to determine the friendly insurgency. Existing works attempted to use continuous subdivisions using time series forecasting and linear regression [16,17] and the Hong Kong protest. However, these machine learning approaches may fail to offer the best accuracy in event forecasting, especially in spatial-temporal data. ...
Nowadays, event forecasting in Twitter can be considered an essential, significant and difficult issue. Maximum conventional methods are focusing on temporal events like sports or elections. These methods do not calculate the spatial features too their correlation analysis. Hence, this paper proposes an Improved Deep Belief Neural Network (iDBNN) for civil unrest event forecasting in twitter data. This proposed method is utilized to forecast the future event with the consideration of the tweets. The proposed method is designed with three phases named as pre-processing phase, feature extraction phase, and civil unrest event forecasting. Initially, the proposed method is used to train the Hong Kong Protest event 2019 tweet data for forecasting events. In the pre-processing phase, removal of special symbol, removal of URL, username removal, tokenization and stop word removal are done. After that, the essential features such as domain weight, event weight, textual similarity, spatial similarity, temporal similarity, and Relative Document-Term Frequency Difference (RDTFD) are extracted and then applied for training the proposed model. To empower the training phase of proposed iDBNN method, the Jellyfish Algorithm is utilized to select optimal weight parameter coefficients of DBNN for training the model parameters. The projected technique is authenticated by statistical capacities and compared with the conventional methods such as Hidden Markov Model (HMM) and Random Forest (RF) respectively. Comparing with other traditional methods, the proposed model shows better performance in terms of prediction and processing time. The iDBNN model shows 91% prediction accuracy that is much higher than the traditional DBNN.
... Event coding has a long history in Political Science, with computer-based datasets being developed that cover inter-state interactions (i.e., between nation-states) going back to the end of the Second World War, typically derived from news sources, with events coded manually, such as COPDAB (Azar, 1980) and WEIS (McClelland, 1978). The KEDS project (Schrodt et al., 1994) was an early example of machine coding, using simple syntactic patterns for event extraction and coding. ...
... Indeed, most of the databases reviewed in the next sections use the same common framework to code event data (typically used for events that merit news coverage, and generally applied to the study of political news and violence) called Conflict and Mediation Event Observations (CAMEO). 99 Other alternative codebook exist, like the World Event/Interaction Survey (WEIS) coding system (Goldstein, 1992;McClelland, 2006) and the Conflict and Peace Data Bank (COPDAB) coding system (Azar, 2009). Here a brief summary of the available on-line resources is presented although how data is generated is not explained in full detail. ...
With the consolidation of the culture of evidence-based policymaking, the availability of data has become central for policymakers. Nowadays, innovative data sources have offered opportunity to describe more accurately demographic, mobility- and migration- related phenomena by making available large volumes of real-time and spatially detailed data. At the same time, however, data innovation has brought up new challenges (ethics, privacy, data governance models, data quality) for citizens, statistical offices, policymakers and the private sector.Focusing on the fields of demography, mobility and migration studies, the aim of this report is to assess the current state of utilisation of data innovation in the scientific literature as well as to identify areas in which data innovation has the most concrete potential for policymaking. For that purpose, this study has reviewed more than 300 articles and scientific reports, as well as numerous tools, that employed non-traditional data sources for demographic, human mobility or migration research.The specific findings of our report contribute to a discussion on a) how innovative data is used in respect to traditional data sources; b) domains in which innovative data have the highest potential to contribute to policymaking; c) prospects for an innovative data transition towards systematic contribution to official statistics and policymaking.
... Beyond disagreements over the classification and the appropriateness of data sources (Silke 2004, p. 61-62), using secondary sources or mixing different datasets aims "to compensate for deficiencies and gaps in the primary source" (Taylor & Hudson 1972, p. 422). In the study of domestic or cross-country violence, data very often stem from media sources that provide certain types of information on violent events (Azar et al. 1972, p. 373;Azar 1980). The usual practice was to rely on a limited number of media collections for generating event data (Jackman & Boyd 1979;Taylor & Hudson 1972). ...
The paper presents a new database (PVGR) on political violence in Greece from 2008
to 2019. PVGR monitors violent episodes reported mainly in online and printed media,
stemming both from the far right and the far left. It provides the first existing measure
of political violence in Greece for a timespan of eleven years. The uniqueness of our
database is two-fold: first, it covers both ideological kinds of extremism: right wing
and left wind; second, it registers the whole stairway of low-intensity violent
escalation, from physical attacks to terrorism. We gather data on all the internalsupply
aspects of political violence: we identify its size, the actors involved and their
ideological background, the targets. We further provide measures of frequency,
intensity, escalation and geographical distribution, which permit us to configure
political violence in crisis-ridden Greece. We find an important increase in political
violence in the period under study. We contribute to the literature of political violence
in several ways. First, we offer the first comprehensive database of political violence
in Greece. Second, we typologize evidence in analytical categories and measures, thus
contributing to the classification of the phenomenon beyond ideological doctrines.
Third, we clarify similarities and differences between the two kinds of violence, which
implies specific policy implications.
... Many human-coded event datasets have been developed and maintained, which allow researchers to build forecasters at specific sub-state geographic units [86,113,140]. In the earliest days, due to technological limitations (i.e., the lack of electronic articles and computational power), the World Event Interaction Survey (WEIS) [84] and the Conflict and Peace Data Bank (COPDAB) [9] projects hire human analysts 1 Dynamic features are usually involved in civil unrest prediction studies, while static features are sometimes not considered. to physically collect newspaper clippings, press reports, and summary accounts from Western news sources to obtain news stories. ...
Population-level societal events, such as civil unrest and crime, often have a significant impact on our daily life. Forecasting such events is of great importance for decision-making and resource allocation. Event prediction has traditionally been challenging due to the lack of knowledge regarding the true causes and underlying mechanisms of event occurrence. In recent years, research on event forecasting has made significant progress due to two main reasons: (1) the development of machine learning and deep learning algorithms and (2) the accessibility of public data such as social media, news sources, blogs, economic indicators, and other meta-data sources. The explosive growth of data and the remarkable advancement in software/hardware technologies have led to applications of deep learning techniques in societal event studies. This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions. We focus on two domains of societal events: \textit{civil unrest} and \textit{crime}. We first introduce how event forecasting problems are formulated as a machine learning prediction task. Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems. Finally, we discuss the challenges in societal event forecasting and put forward some promising directions for future research.
... Basic need theories have also contributed a great deal to PACS and discussions on positive peace. Peace scholar, John Burton (1990), argued that the universal needs of human beings must be fulfilled in order to prevent or resolve conflict, and scholar Edward Azar (1980), who developed the protracted social conflict theory, 9 associated conflicts with needs such as security, identity, recognition and participation. Johan Galtung (2012) identified four basic needs of humanity: ...
People with disabilities are the largest minority in the world; a minority that continues to face high instances of direct, structural and cultural violence during times of peace, as well as during times of conflict and displacement. Exacerbating their marginalisation has been the absence of the disability community from Peace and Conflict Studies (PACS) research, literature and practice, which has perpetuated ableist ideologies and hindered the pursuit of “positive peace”. This research responds to this absence by investigating the intersectionality of disability, conflict and displacement from a PACS perspective. Its purpose is two-fold. The first aim is to conduct pure research that challenges the on-going marginalisation of people affected by disability, conflict and displacement, by intentionally de-subjugating and valuing their knowledge and experiences. The second aim is to use applied research to conceptualise and demonstrate ways in which PACS might actively advance inclusive and accessible positive peace. The design of this research was strongly influenced by critical theories, the transformative paradigm, appreciative inquiry, narrative inquiry and partial-insider research. Over a period of five weeks, twenty interviews were conducted in Ecuador with refugees and asylum seekers with disabilities from Colombia and Venezuela, and their family members. A further five interviews were conducted with service providers. The key findings were simple. Participants confirmed that the intersectional experience of disability, conflict and displacement can be dangerous and harrowing. As participants shared insights into how to navigate direct, structural and cultural violence during conflict and displacement, a second key finding was that a great deal can be learned from people with lived experience. Finally, this research revealed that when PACS is informed by rights-based approaches; when those with lived experience have equitable opportunities to determine their own research agenda and contribute knowledge and expertise; and when “nothing about us, without us” is at the forefront of peacebuilding research and activities, then inclusive and accessible positive peace can begin to be realised.
... Tidligere innholdsanalyser av hendelser som har oppstått på bakgrunn av staters handlinger, har også fokusert på egenskaper ved verb som for eksempel intensitet i konflikt, samarbeid og deltakelse på den internasjonale politiske arena (f.eks. Azar 1980;Callahan, Brady & Hermann 1982;Goldstein 1992). ...
... 30 The verb as the center for analysis has figured as relevant in several content analytical works prior to the full development of OPCODE. 31 It is beyond the scope of this article to present the VICS system in its entirety, we shall at this point only carry the basics, wherein the Romanian Political Science Review vol. XX no. 4 2020 "two linguistic components, the subject and the verb, combine to form the recording unitcalled the 'utterance'-for the VICS system. ...
Slobodan Milošević, a key figure in the Yugoslav conflicts of the nineties, has been the focus of much scholarly analysis. However, we have, chosen to tackle him from the perspective of Operational Code Analysis, which is most commonly used for delving into political beliefs (dubbed "philosophical" and "instrumental" within the methodology) of political leaders. For the analysis of his Operational Code, we have coded his speeches at the Congresses of the Socialist Party of Serbia (whose president he was), which was the ruling party in Serbia during the nineties, his 1989 Kosovo Field speech (from when he rose to prominence), and his 2001 reflection on the Hague Tribunal, as the beginning and end of his political career. Furthermore, and arguably more important, is the novel approach to Operational Code Analysis, wherein it goes from its initial idea of analyzing the "inner" political beliefs of the chosen political subject to the Weltanschauung that they promulgate in practice. This is based on the switch from Platonic idealism towards Aristotle, drawing as well from Sartre, and Speech-Act theory developed by Austin and Searle. The approach has been dubbed "practical political hematology", as it functions similarly to a medical blood screening: it divulges a set of practical political beliefs not unlike the blood screening in relation to the human bodily functions.
... The ICEWS dataset grew out of a large body of academic research 6 on using discrete events for studying international (and domestic) relations (McClelland 1976;Azar 1980;Goldstein 1992). The results of such data collection are applicable to my coding of soft and hard power actions. ...
The soft power literature has indicated that American soft power use has been declining while Russian and Chinese soft power use has been increasing. Until now, the only way scholars could test such claims was to compare these countries' soft power rankings. This paper uses a new soft power dataset that can evaluate countries' soft power use. Using this dataset, this paper tests three hypothesis regarding China's, Russia's and the US' soft power use for the time-period of 1995-2015. The findings indicate that surprisingly the US is still using more soft power than Russia and China. The data analysis also reveals that the US is leading in economic soft power actions over China and in military soft power actions over Russia as well.
... Fortunately, with the development of data science, especially the rise of big data, there are more and more data-driven approaches proposed on microscopic insight into possible social unrest events. Last century, most researchers conducted the prediction work using human-coded data, including WEIS [2] and COPDAB [3]. In the recent two decades, several small-scale vertical machine-readable datasets [4,5] and large-scale coded event data like ICEWS (Integrated Crisis Early Warning System) [6] and GDELT [7] appeared, fueling the development of computation methods for the analysis and prediction of social unrest. ...
Social unrest events are common happenings in modern society which need to be proactively handled. An effective method is to continuously assess the risk of upcoming social unrest events and predict the likelihood of these events. Our previous work built a hidden Markov model- (HMM-) based framework to predict indicators associated with country instability, leaving two shortcomings which can be optimized: omitting event participants’ interaction and implicitly learning the state residence time. Inspired by this, we propose a new prediction framework in this paper, using frequent subgraph patterns and hidden semi-Markov models (HSMMs). The feature called BoEAG (Bag-of-Event-Association-subGraph) is constructed based on frequent subgraph mining and the bag of word model. The new framework leverages the large-scale digital history events captured from GDELT (Global Data on Events, Location, and Tone) to characterize the transitional process of the social unrest events’ evolutionary stages, uncovering the underlying event development mechanics and formulating the social unrest event prediction as a sequence classification problem based on Bayes decision. Experimental results with data from five main countries in Southeast Asia demonstrate the effectiveness of the new method, which outperforms the traditional HMM by 5.3% to 16.8% and the logistic regression by 11.2% to 43.6%.
Experiencing repression creates intense emotions and raises dilemmas about handling political action to achieve social change. Past studies suggest that mainly group-based emotions are associated with support for violent collective action while the exact influence of individual emotions remains unclear. This research compares the association of individual- versus group-based emotions with violent collective action while examining conflict context as the moderating factor. We propose to distinguish two context aspects—collective versus personal threat—determining the relative impact of individual versus group emotions on support for violence. We conducted two quantitative field studies in the Occupied Palestinian Territories during different types of conflict experience, defined by either prevalent personally experienced threat versus elevated collectively experienced threat (Study 1), or both (Study 2). Results indicate that for mainly collectively experienced threat, group (but not individual) emotions predicted violent collective action, while for personally experienced threat, individual (but not group) emotions predicted violent engagement.
The Sino–Russian relationship is of fundamental importance to the global order. Following the question of how this relationship has developed over time—whether it has strengthened, weakened or remained constant—we present a quantitative analysis of its evolution between 1992 and 2019. To this end, the study develops an original index, the Bilateral Cooperation Intensity (BCI) Index, aimed at measuring bilateral (Sino–Russian) cooperation and considering specific (military, economic, political) dimensions. While our findings verify the assumption that China and Russia have indeed strengthened their cooperation in a progressive manner, with no apparent setback following Russia’s 2014 annexation of Crimea, the results do not corroborate the claims of dramatic change frequently presented in the literature.
Chapter 2 reviews a large portion (roughly 230 articles) of the more recent quantitative literature on conflict and cooperation dynamics in international politics that involve some effort to include “region” as part of the analysis. The review notes that while there is little consensus regarding the definitionRegiondefinition and operationalization of “region”, most studies identifying regions report substantial and significant region effectsRegioneffects on the dependent variable of interest. In order the move towards a more comprehensive analysis of region effectsRegioneffects, the chapter proposes a new approach to conceptualizing and delineating regions on the basis of an opportunity and willingness frameworkOpportunity and willingness framework for regional delineation. Applying the approach, it then identifies the changing nature of regions and their membership in both Cold WarCold Warand post-Cold WarPost-Cold War eras and discusses both the strengths and limitations of the approach. Then he chapter proposes a theoretical framework for examining conflict, cooperation, and diffusion dynamics across regions. It suggests three types of regional effects, but places primary emphasis on a comparative regional analysis that discriminates between regions based on differences created by hierarchical relationships both inside regions and globally, integrating structural approaches into the theoretical framework. The chapter concludes with suggestions for future research and a series of caveats regarding both the identification of regions and the utility of the proposed framework.
There are regional variations in the way conflict and peace are enacted around the world. For instance, there may be differences in the extent to which any conflict is likely to occur and in whether a conflict is currently taking place.
Building on the debate on engaged scholarship in project studies, this article aims to explore the extent and potential of practitioner involvement in research on projects and thereby characterise the evolution of the field through the lens of engaged scholarship. We conduct a longitudinal bibliometric analysis of 6584 articles published on projects between 1964 and 2017 to capture the volume and citation impact of publications featuring practitioner involvement in comparison to purely academic publications. The analysis identifies distinct research production patterns, allowing us to delineate and characterise three evolutionary periods in project studies: projects as an execution methodology (1964-1989), projects as an organisational concept (1990-2001), and projects as a theoretical framework (from 2002). In this way, the article enriches the ongoing debate about engaged scholarship in project studies, and discusses the endemic challenges, as well as unused potential, of actively involving practitioners in the production of research on projects.
The relationship between the ROK and DPRK is bound to be affected by the two great powers—the US and China. Especially in recent decades, the power gap between the two great powers has continued to narrow. Given this, how is the geopolitical situation surrounding the Korean Peninsula shaping inter-Korean relations? This study uses event data and statistical analysis to explore the geopolitical factors that shaped inter-Korean relations from 1993 to 2019. We find that DPRK–ROK relations deteriorated as the power gap between the US and China narrowed. Also, inter-Korean relations were positive when DPRK–US relations were positive. In short, we conclude that during the shift in the US–China power distribution, maintaining positive DPRK–US relations while also managing inter-Korean relations peacefully is necessary for peace on the Korean Peninsula.
This chapter summarizes the results of a 15 year experimental political psychological research program concerning how decisions are made regarding war, peace, and terrorism.
This study explores that CPEC is the mega driver of globalization and instrument of soft balancing and can bring economic equilibrium through development and interconnectivity to bridge parity in soft power between Indian and Pakistan , which has been mega impediment of positive peace. The study at hand had tested the framework ofInternational Economic Leverage and Its Uses,to understand the nature, magnitude and layers of Sino-Pakistan Interdependence and its implications to maintain regional balance in South Asia and address the impasse between India and Pakistan. The study reveals that regional connectivity in the shape of CPEC carries economical leverage to bring quantum of parity between India and Pakistan which can bring fourth chance as potent catalyst to address the Kashmir Issue. The degree of interdependency will have multi dimensional spillover effects, if OBOR is extended and developed in Azad Jammu and Kashmir. It has natural pessage through AJ&K, via Khunjerab, along Neelam River having a natural junction with Srinagar Rawalpindi Road at Domail, Muzaffarabad. This route has been connecting Srinagar through trade and travel since 2008, through LoC. The paper suggests that It leads to a logical sequence, where the entire state of Jammu and Kashmir from both sides of LoC is declared as 'free economic zone in five phases', keeping speedy driver of globalization in the shape of OBOR in consideration. It will be mega Kashmir centric CBM and a major catalyst of conflict resolution.
This chapter presents an overview of what is known about mediation (as of 2014) by two well-known mediation researchers. It goes into the definition, data, frequency and strategies of mediation. It also discusses particular problems, such as mediator bias and coordination between mediation efforts. Finally, it raises matters of outcomes of mediation and challenges for continued mediation research.
Since the Syrian conflict has been going on for over ten years, it is often stated that the civil war in that country became protracted or intractable. In addition, the emphasis on the sectarian dimension of the conflict draws attention to the social and religious structure of the Syrian population. In spite of these characteristics of the conflict, the Syrian civil war has been rarely associated with Edward Azar's theory of protracted social conflict (PSC). This paper tries to explain the Syrian civil war with the theory of PSC that presents a multi-dimensional approach. Thus, it is argued that a crisis of legitimacy that stems from socioeconomic and sectarian imbalances triggered the civil war in Syria.
Event extraction (EE) is one of the core information extraction tasks, whose purpose is to automatically identify and extract information about incidents and their actors from texts. This may be beneficial to several domains such as knowledge base construction, question answering and summarization tasks, to name a few. The problem of extracting event information from texts is longstanding and usually relies on elaborately designed lexical and syntactic features, which, however, take a large amount of human effort and lack generalization. More recently, deep neural network approaches have been adopted as a means to learn underlying features automatically. However, existing networks do not make full use of syntactic features, which play a fundamental role in capturing very long-range dependencies. Also, most approaches extract each argument of an event separately without considering associations between arguments which ultimately leads to low efficiency, especially in sentences with multiple events. To address the above-referred problems, we propose a novel joint event extraction framework that aims to extract multiple event triggers and arguments simultaneously by introducing shortest dependency path in the dependency graph. We do this by eliminating irrelevant words in the sentence, thus capturing long-range dependencies. Also, an attention-based graph convolutional network is proposed, to carry syntactically related information along the shortest paths between argument candidates that captures and aggregates the latent associations between arguments; a problem that has been overlooked by most of the literature. Our results show a substantial improvement over state-of-the-art methods on two datasets, namely ACE 2005 and TAC KBP 2015.
This article seeks to explore the determinants of China-ROK relations during the period 1993–2018, employing event data and statistical analysis. The analysis found that China’s trade dependence on ROK, and vice versa, had a positive effect on China-ROK relations. The relations were also positively affected by China’s economic development. In contrast, the relations were negatively affected as China’s population aged and while conservative administrations governed ROK. The empirical findings of this article provide essential insights, identifying the factors that promote or hinder the development of cooperative China-ROK relations, suggesting guidelines to policymakers on both sides.
The central aim of the paper is to state and prove a representation theorem for finite automata in terms of models of stimulus-response theory. The main theorem is that, given any connected finite automaton, there is a stimulus-response model that asymptotically becomes isomorphic to it. Implications of this result for language learning are discussed in some detail. In addition, an immediate corollary is that any tote hierarchy in the sense of Miller and Chomsky is isomorphic to some stimulus-response model at asymptote. Representations of probabilistic automata are also discussed, and an application to the learning of arithmetic algorithms is given.
In this article some problems of scaling events data are re‐examined with a focus on apparent discontinuities, particularly at the cooperation end of the scales. The authors offer some possible interpretations of the “gaps” in both the international and domestic scales, and conclude with a discussion of three strategies (paradigms) for conceptualizing a theory of cooperation.
When defining their immediate situations, people characterize themselves and others by social identities like doctor and patient, evoking sentiments that serve as guidelines for interpreting and creating events in the given situation. In particular, the assigned identities recall notions of how good, how powerful, and how lively each person is fundamentally. When events deflect feelings away from these sentiments, new events are conceived and ordinarily implemented to move feelings back toward the fundamental values. Thus, theoretically, social behavior and transient feelings form a control system with fundamental sentiments as reference signals. Interpersonal conflicts sometimes lead to events that a person cannot comprehend as sentiment confirming. This invokes redefinitions of situations, a higher order control that changes reference signals. Empirically derived formulas describing affective reactions to events have been elaborated into a mathematical model representing all of these processes. Data on a large number of social identities and behaviors have been collected to permit simulations using the model. Illustrations show that this theory of social action permits concrete, plausible analyses of social interactions, role relationships, and social reactions to deviance. Simulations of group dynamics in organizational contexts conceivably could provide guidelines for changing group functioning and for establishing social structures without historical precedent.
It is possible to construct a basic framework that potentially accommodates the interactions of all biological, biosocial, cultural and situational determinants of behavior. While specific problems will require changes of detail, a single structure of interactions for all problems increases the additive possibilities of the field, and makes feasible definition of the limits and applicability of alternative general theories. The framework should help the applied social scientist relate his suggestions to the full range of interactions.
Stimulus-response theory of finite automata Contemporary Research in International Relations
- P Suppes
SUPPES, P. (1969) "Stimulus-response theory of finite automata." J. of hlathematical ZINNES, D. A. (1976) Contemporary Research in International Relations. Kew York: PA: International Studies Association.
“An early warning model of international hostilities, ”
- A Rapoport
“Ten issues in events research, ”
- A Rapoport
“International relations: contributions from the International Encyclopedia of Social Sciences.”
- H Alker
- P G Boch
“Analysis of international events.”
- A Rapoport
Dimensions of Interaction: A Source Book
- A Rapoport
- T Sloan
Computer Assisted Analysis of Social Events Using Program Interact and Survey. Chapel Hill: IRSS
- D Heise
“Social action as a theory of affect.”
- D Heise