MATH WORLD

We recently began analyzing the ACLED (Armed Conflict Location & Event Data) dataset as part of a collaborative data exploration project. This dataset provides real-time information on political violence, protests, and conflict events from around the world. We started by cleaning and preprocessing the data—handling missing values, filtering events by region and time period, and aggregating key metrics like fatalities and event types. Using visualizations such as time-series plots, heatmaps, and bar charts, we explored trends over the years, identified conflict hotspots, and gained insights into the most active groups and regions.

As we progressed, we moved into more advanced analyses, including clustering similar conflict patterns, comparing different countries, and visualizing events on interactive geospatial maps. We also plan to integrate other datasets, like economic indicators or climate data, to investigate potential correlations with conflict trends. Working together on this project has been both educational and eye-opening, helping us understand how data can reveal hidden patterns in global conflict. We’re excited to continue our journey with ACLED and share more of our findings along the way.

In class, we discussed our proposed project 2 question and received valuable feedback from the professor. He provided suggestions to help refine our question and ensure the project is more focused and feasible.

In this lecture, Professor Gary introduced a new dataset from ACLED, which documents political violence and protest events worldwide. I examined the dataset, exploring its structure, key attributes, and trends. The data includes details such as event types, locations, dates, and actors involved, providing a comprehensive view of conflict and unrest patterns. While reviewing, I noticed variations in data distribution across different regions and time periods, which could offer valuable insights for further analysis. This dataset seems to be a rich resource for studying geopolitical conflicts, trends in civil unrest, and the impact of political movements.

The Armed Conflict Location and Event Data (ACLED) organization provides a comprehensive, real-time dataset that tracks political violence, including protests, riots, and armed conflicts across the globe. ACLED’s primary goal is to offer detailed, reliable, and timely data to support researchers, policymakers, and organizations in understanding the dynamics of political instability. The data is collected through open sources such as media reports, government documents, and NGOs, allowing ACLED to track various events and categorize them by location, date, type of violence, and the parties involved.

In the context of India, ACLED data sheds light on the frequency, scale, and nature of protests, as well as their geographic distribution. The data helps answer essential questions, such as the trends in protest events over time, identifying which states or districts experience the highest frequency of demonstrations. ACLED also distinguishes between different types of protests, such as peaceful marches, strikes, or violent confrontations, which are crucial in understanding the political climate and public sentiment.

Questions:
Are there seasonal patterns in protest occurrences (e.g., more protests in election years)?

• What are the key issues driving protests in different states of India?

• Are protests in India more common in metropolitan cities compared to smaller towns and villages?

• What are the most common types of demonstrations?
• What percentage of protests result in arrests or legal actions?

In this weekend’s math class, Mahnoor presented her analysis of the police shooting data. In her analysis, she found that individuals of a particular race are shot more frequently compared to their overall population percentage.

MY REPORT:

My teammate Sampadaa and I are working on our report. I preprocessed the dataset using some code, and then we began working on the report. The preprocessing steps were done by me, and my teammate started building graphs and charts to gain a clearer understanding of the data

Police Shooting :

When I analyzed the Washington Police shooting Dataset. I found that the dataset contains 10,045 records with several attributes, includes gender, weapon, race, name, state , city, body came ,mental illness and the police department involves.

The dataset shows that different types weapons were used in this incident such as  gun, knife blunt object as well as unarmed cases where no weapon was involved.

various police departments were involved in these police shooting with  Los Angeles ,Phoenix ,New York ,Houston and San Antonio.

Regarding gender, the majority of victims were male, accounting for approximately 9,588 (95%) while Female Victims accounted for about 448(4.5%).  This analysis indicates that men are significantly more likely to be victims of police shootings compared to female and a portion of these cases involved individuals with mental illness.

Questions:

1. How many police shooting involved individuals with mental illness?
2. Which age group is most frequently involved in police shootings?
3. Which state has the highest number of police shooting?
4. Are there any cities with high number of police shooting?
5. What is the distribution of police shootings across different months and years?
6. Are there any pattern in the involvement of specific police departments over time?

On the second day we had a discussion with various questions about fatal police shootings.

While discussing questions with Professor Gary Davis we explored various topics such as the cause of police shootings.Do these shootings happen due to bank robberies or other thefts?If I had that data,I could analyze it.

• Do police shootings occur due to the crime rate in the area?

On the first day of the Advanced Mathematical Statistics class,Professor Gary Davis presented an Excel dataset related to Police Shooting.

• I observed that the dataset focuses on police shootings. To understand it better,I first analyzed it using Microsoft Excel and found that it is related to Washington Police Shooting.
• While analyzing the data,I noticed that police shootings are categorized by attributes such as name, age, genders ,race ,weapon type, mental health signs and body camera usage. The data has different locations and includes people of various races and gender.Most of the cases involve white males, but also instances involve females and people from other racial groups like blacks.
• These are the things I learned during the first Lecture of MTH.
• While analyzing this data,I had some questions in mind.

1. Why are these shootings happening?
2. Which state has highest death rate?
3. What actions can we taken to prevent shootings?