Vito D’orazio
Biographic Data
| ID | 1417915 |
|---|---|
| NAME | Vito D’orazio |
| GIVEN NAMES | Vito |
| FAMILY NAME | D’orazio |
| SIGNATURE | D’ORAZIO V |
| AFFILIATIONS | West Virginia University |
| ORCID | 0000-0003-4249-0768 |
| VERIFIED | Yes |
| TOTAL WORKS | 13 |
| TOTAL CITATIONS | 260 |
| WORKS AS AUTHOR | 13 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2012 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 6 |
Extractive versus Generative Language Models for Political Conflict Text Classification
We review our recent ConfliBERT language model (Hu et al . 2022 [ConfliBERT: A Pre-Trained Language Model for Political Conflict and Violence]) to process political and violence-related texts. When fine-tuned, results show that ConfliBERT has superior performance in accuracy, precision, and recall over other large language models (LLMs) like Google’s Gemma 2 (9B), Meta’s Llama 3.1 (7B), and Alibaba’s Qwen 2.5 (14B) within its relevant domains. It…
Elections and Anti-Refugee Violence in Germany from 2014-2020
Electoral violence can influence and even delegitimize electoral contests. Yet, much of the research on electoral violence excludes established democracies. As a result, we know relatively little about the relationship between elections and political violence in these states. This paper explores the relationship between anti-refugee violence, a type of political violence, and elections in Germany during the refugee influx of the 2010s. Despite th…
The 2023/24 Views Prediction challenge
Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fa…
Forecasting conflict in Africa with automated machine learning systems
The ViEWS problem is to forecast changes in the level of state-based violence for each of the next six months at the PRIO-GRID and country level. For this competition and toward the goal of improving sub-national and country level forecasts, we experiment with combinations of automated machine learning (autoML) systems and limited datasets that emphasize the endogenous nature of conflict. Two core findings emerge: autoML improves predictive perfo…
Conflict forecasting with event data and spatio-temporal graph convolutional networks
This paper explores three different model components to improve predictive performance over the ViEWS benchmark: a class of neural networks that account for spatial and temporal dependencies; the use of CAMEO-coded event data; and the continuous rank probability score (CRPS), which is a proper scoring metric. We forecast changes in state based violence across Africa at the grid-month level. The results show that spatio-temporal graph convolutiona…
The MID5 Dataset, 2011–2014
This article introduces the latest iteration of the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 5 dataset. We begin by outlining the data collection process used in the MID5 project. Next, we discuss some of the most challenging cases that we coded and some updates to the coding manual that resulted. Finally, we provide descriptive statistics for the new years of the MID data
The Militarized Interstate Dispute Dataset
In their latest research note in our ongoing dialogue about the Militarized Interstate Dispute (MID) dataset, Gibler, Miller, and Little (GML) reiterate their concerns about a high error rate in the MID dataset and challenge our prior replication studies, which showed that GML's recommended changes to the dataset caused few substantive changes in the core findings of two published studies. In this rejoinder, we offer further explanation of our de…
Buying blue helmets
While the evolving nature and proliferation of UN peacekeeping operations in the post-Cold War period is well documented, we know less about how personnel are recruited for these missions. Furthermore, recent developments have rendered existing supply-side explanations for troop contributions less convincing. The increasing demand for personnel, along with stagnant UN reimbursement rates and the rising costs of participation that began during the…
Updating the Militarized Interstate Dispute Data
In a recent article, Gibler, Miller, and Little (2016) (GML) conduct an extensive review of the Militarized Interstate Dispute (MID) data between the years 1816 and 2001, highlighting possible inaccuracies and recommending a substantial number of changes to the data. They contend that, in several instances, analyses with their revised data lead to substantively different inferences. Here, we review GML's MID drop and merge recommendations and ree…
Who is a Terrorist? Ethnicity, Group Affiliation, and Understandings of Political Violence
What does the American public label as “terrorism?” How do people think about the factors motivating violence, and in turn, the policies that are favored? Using ingroup and outgroup dynamics, we argue that the terrorist label is more readily applied to Arab-Americans than Whites, and to members of militant groups. Moreover, people attribute different motives to violence committed by Arabs versus Whites, and favor different policies in response. W…
The MID4 dataset, 2002–2010
Understanding the causes of interstate conflict continues to be a primary goal of the field of international relations. To that end, scholars continue to rely on large datasets of conflict in the international system. This paper introduces the latest iteration in the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 4 data. In this paper we first outline the updated data-collection process for the MID4 dat…
Separating the Wheat from the Chaff
Due in large part to the proliferation of digitized text, much of it available for little or no cost from the Internet, political science research has experienced a substantial increase in the number of data sets and large-nresearch initiatives. As the ability to collect detailed information on events of interest expands, so does the need to efficiently sort through the volumes of available information. Automated document classification presents …
War Games
Since 1976, the militaries of the United States and South Korea have been holding routine joint military exercises (JMEs) for the purposes of military training and deterrence against North Korea. These exercises are frequently cited as a cause of tension on the peninsula, causing North Korea to escalate its conflictual rhetoric and behavior. I empirically assess this claim using new data on US-ROK JMEs and machine-coded event data collected by th…
The MID4 dataset, 2002–2010
Understanding the causes of interstate conflict continues to be a primary goal of the field of international relations. To that end, scholars continue to rely on large datasets of conflict in the international system. This paper introduces the latest iteration in the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 4 data. In this paper we first outline the updated data-collection process for the MID4 dat…
The MID5 Dataset, 2011–2014
This article introduces the latest iteration of the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 5 dataset. We begin by outlining the data collection process used in the MID5 project. Next, we discuss some of the most challenging cases that we coded and some updates to the coding manual that resulted. Finally, we provide descriptive statistics for the new years of the MID data
Who is a Terrorist? Ethnicity, Group Affiliation, and Understandings of Political Violence
What does the American public label as “terrorism?” How do people think about the factors motivating violence, and in turn, the policies that are favored? Using ingroup and outgroup dynamics, we argue that the terrorist label is more readily applied to Arab-Americans than Whites, and to members of militant groups. Moreover, people attribute different motives to violence committed by Arabs versus Whites, and favor different policies in response. W…
Updating the Militarized Interstate Dispute Data
In a recent article, Gibler, Miller, and Little (2016) (GML) conduct an extensive review of the Militarized Interstate Dispute (MID) data between the years 1816 and 2001, highlighting possible inaccuracies and recommending a substantial number of changes to the data. They contend that, in several instances, analyses with their revised data lead to substantively different inferences. Here, we review GML's MID drop and merge recommendations and ree…
Separating the Wheat from the Chaff
Due in large part to the proliferation of digitized text, much of it available for little or no cost from the Internet, political science research has experienced a substantial increase in the number of data sets and large-nresearch initiatives. As the ability to collect detailed information on events of interest expands, so does the need to efficiently sort through the volumes of available information. Automated document classification presents …
War Games
Since 1976, the militaries of the United States and South Korea have been holding routine joint military exercises (JMEs) for the purposes of military training and deterrence against North Korea. These exercises are frequently cited as a cause of tension on the peninsula, causing North Korea to escalate its conflictual rhetoric and behavior. I empirically assess this claim using new data on US-ROK JMEs and machine-coded event data collected by th…
Buying blue helmets
While the evolving nature and proliferation of UN peacekeeping operations in the post-Cold War period is well documented, we know less about how personnel are recruited for these missions. Furthermore, recent developments have rendered existing supply-side explanations for troop contributions less convincing. The increasing demand for personnel, along with stagnant UN reimbursement rates and the rising costs of participation that began during the…
Forecasting conflict in Africa with automated machine learning systems
The ViEWS problem is to forecast changes in the level of state-based violence for each of the next six months at the PRIO-GRID and country level. For this competition and toward the goal of improving sub-national and country level forecasts, we experiment with combinations of automated machine learning (autoML) systems and limited datasets that emphasize the endogenous nature of conflict. Two core findings emerge: autoML improves predictive perfo…
Conflict forecasting with event data and spatio-temporal graph convolutional networks
This paper explores three different model components to improve predictive performance over the ViEWS benchmark: a class of neural networks that account for spatial and temporal dependencies; the use of CAMEO-coded event data; and the continuous rank probability score (CRPS), which is a proper scoring metric. We forecast changes in state based violence across Africa at the grid-month level. The results show that spatio-temporal graph convolutiona…
The Militarized Interstate Dispute Dataset
In their latest research note in our ongoing dialogue about the Militarized Interstate Dispute (MID) dataset, Gibler, Miller, and Little (GML) reiterate their concerns about a high error rate in the MID dataset and challenge our prior replication studies, which showed that GML's recommended changes to the dataset caused few substantive changes in the core findings of two published studies. In this rejoinder, we offer further explanation of our de…
War Games
Since 1976, the militaries of the United States and South Korea have been holding routine joint military exercises (JMEs) for the purposes of military training and deterrence against North Korea. These exercises are frequently cited as a cause of tension on the peninsula, causing North Korea to escalate its conflictual rhetoric and behavior. I empirically assess this claim using new data on US-ROK JMEs and machine-coded event data collected by th…
Separating the Wheat from the Chaff
Due in large part to the proliferation of digitized text, much of it available for little or no cost from the Internet, political science research has experienced a substantial increase in the number of data sets and large-nresearch initiatives. As the ability to collect detailed information on events of interest expands, so does the need to efficiently sort through the volumes of available information. Automated document classification presents …
The MID4 dataset, 2002–2010
Understanding the causes of interstate conflict continues to be a primary goal of the field of international relations. To that end, scholars continue to rely on large datasets of conflict in the international system. This paper introduces the latest iteration in the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 4 data. In this paper we first outline the updated data-collection process for the MID4 dat…
Who is a Terrorist? Ethnicity, Group Affiliation, and Understandings of Political Violence
What does the American public label as “terrorism?” How do people think about the factors motivating violence, and in turn, the policies that are favored? Using ingroup and outgroup dynamics, we argue that the terrorist label is more readily applied to Arab-Americans than Whites, and to members of militant groups. Moreover, people attribute different motives to violence committed by Arabs versus Whites, and favor different policies in response. W…
Updating the Militarized Interstate Dispute Data
In a recent article, Gibler, Miller, and Little (2016) (GML) conduct an extensive review of the Militarized Interstate Dispute (MID) data between the years 1816 and 2001, highlighting possible inaccuracies and recommending a substantial number of changes to the data. They contend that, in several instances, analyses with their revised data lead to substantively different inferences. Here, we review GML's MID drop and merge recommendations and ree…
The Militarized Interstate Dispute Dataset
In their latest research note in our ongoing dialogue about the Militarized Interstate Dispute (MID) dataset, Gibler, Miller, and Little (GML) reiterate their concerns about a high error rate in the MID dataset and challenge our prior replication studies, which showed that GML's recommended changes to the dataset caused few substantive changes in the core findings of two published studies. In this rejoinder, we offer further explanation of our de…
Buying blue helmets
While the evolving nature and proliferation of UN peacekeeping operations in the post-Cold War period is well documented, we know less about how personnel are recruited for these missions. Furthermore, recent developments have rendered existing supply-side explanations for troop contributions less convincing. The increasing demand for personnel, along with stagnant UN reimbursement rates and the rising costs of participation that began during the…
The MID5 Dataset, 2011–2014
This article introduces the latest iteration of the most widely used dataset on interstate conflicts, the Militarized Interstate Dispute (MID) 5 dataset. We begin by outlining the data collection process used in the MID5 project. Next, we discuss some of the most challenging cases that we coded and some updates to the coding manual that resulted. Finally, we provide descriptive statistics for the new years of the MID data
Forecasting conflict in Africa with automated machine learning systems
The ViEWS problem is to forecast changes in the level of state-based violence for each of the next six months at the PRIO-GRID and country level. For this competition and toward the goal of improving sub-national and country level forecasts, we experiment with combinations of automated machine learning (autoML) systems and limited datasets that emphasize the endogenous nature of conflict. Two core findings emerge: autoML improves predictive perfo…
Conflict forecasting with event data and spatio-temporal graph convolutional networks
This paper explores three different model components to improve predictive performance over the ViEWS benchmark: a class of neural networks that account for spatial and temporal dependencies; the use of CAMEO-coded event data; and the continuous rank probability score (CRPS), which is a proper scoring metric. We forecast changes in state based violence across Africa at the grid-month level. The results show that spatio-temporal graph convolutiona…
Extractive versus Generative Language Models for Political Conflict Text Classification
We review our recent ConfliBERT language model (Hu et al . 2022 [ConfliBERT: A Pre-Trained Language Model for Political Conflict and Violence]) to process political and violence-related texts. When fine-tuned, results show that ConfliBERT has superior performance in accuracy, precision, and recall over other large language models (LLMs) like Google’s Gemma 2 (9B), Meta’s Llama 3.1 (7B), and Alibaba’s Qwen 2.5 (14B) within its relevant domains. It…
Elections and Anti-Refugee Violence in Germany from 2014-2020
Electoral violence can influence and even delegitimize electoral contests. Yet, much of the research on electoral violence excludes established democracies. As a result, we know relatively little about the relationship between elections and political violence in these states. This paper explores the relationship between anti-refugee violence, a type of political violence, and elections in Germany during the refugee influx of the 2010s. Despite th…
The 2023/24 Views Prediction challenge
Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fa…
Computer Science (9 works) · Political science (8 works) · Law (7 works) · Artificial Intelligence (5 works) · Economics (5 works) · Law (5 works) · Politics (4 works) · Computational and Text Analysis Methods (3 works) · Data mining (3 works) · Data science (3 works)