Matching Items (9)

Filtering by

Clear all filters

Detecting Propaganda Bots on Twitter Using Machine Learning

Description

Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on

Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on Twitter, I determined that I could train algorithms to detect these bots. The paper focuses on my development and process of training classifiers and using them to create a user-facing server that performs prediction functions automatically. The learning goals of this project were detailed, the focus of which was to learn some form of machine learning architecture. I needed to learn some aspect of large data handling, as well as being able to maintain these datasets for training use. I also needed to develop a server that would execute these functionalities on command. I wanted to be able to design a full-stack system that allowed me to create every aspect of a user-facing server that can execute predictions using the classifiers that I design.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.

Contributors

Agent

Created

Date Created
2019-05

133143-Thumbnail Image.png

Analysis of BoostOR: A Twitter Bot Detection Classification Algorithm

Description

The prevalence of bots, or automated accounts, on social media is a well-known problem. Some of the ways bots harm social media users include, but are not limited to, spreading misinformation, influencing topic discussions, and dispersing harmful links. Bots have

The prevalence of bots, or automated accounts, on social media is a well-known problem. Some of the ways bots harm social media users include, but are not limited to, spreading misinformation, influencing topic discussions, and dispersing harmful links. Bots have affected the field of disaster relief on social media as well. These bots cause problems such as preventing rescuers from determining credible calls for help, spreading fake news and other malicious content, and generating large amounts of content which burdens rescuers attempting to provide aid in the aftermath of disasters. To address these problems, this research seeks to detect bots participating in disaster event related discussions and increase the recall, or number of bots removed from the network, of Twitter bot detection methods. The removal of these bots will also prevent human users from accidentally interacting with these bot accounts and being manipulated by them. To accomplish this goal, an existing bot detection classification algorithm known as BoostOR was employed. BoostOR is an ensemble learning algorithm originally modeled to increase bot detection recall in a dataset and it has the possibility to solve the social media bot dilemma where there may be several different types of bots in the data. BoostOR was first introduced as an adjustment to existing ensemble classifiers to increase recall. However, after testing the BoostOR algorithm on unobserved datasets, results showed that BoostOR does not perform as expected. This study attempts to improve the BoostOR algorithm by comparing it with a baseline classification algorithm, AdaBoost, and then discussing the intentional differences between the two. Additionally, this study presents the main factors which contribute to the shortcomings of the BoostOR algorithm and proposes a solution to improve it. These recommendations should ensure that the BoostOR algorithm can be applied to new and unobserved datasets in the future.

Contributors

Agent

Created

Date Created
2018-12

137174-Thumbnail Image.png

Analysis of Twitter's Effect on Stock Prices

Description

Twitter has become a very popular social media site that is used daily by many people and organizations. This paper will focus on the financial aspect of Twitter, as a process will be shown to be able to mine data

Twitter has become a very popular social media site that is used daily by many people and organizations. This paper will focus on the financial aspect of Twitter, as a process will be shown to be able to mine data about specific companies' stock prices. This was done by writing a program to grab tweets about the stocks of the thirty companies in the Dow Jones.

Contributors

Agent

Created

Date Created
2014-05

136516-Thumbnail Image.png

Categorizing and Discovering Social Bots

Description

Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then

Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots.

Contributors

Created

Date Created
2015-05

Section 230 Reform: A Mirror into the Divisive Socio-Political Landscape in America

Description

Over the past couple of years, the focus on the prevalence of hate-speech and misinformation on the internet has increased. Lawmakers feel that repealing or reforming Section 230 of the Communication Decency Act is the way to go, considering that

Over the past couple of years, the focus on the prevalence of hate-speech and misinformation on the internet has increased. Lawmakers feel that repealing or reforming Section 230 of the Communication Decency Act is the way to go, considering that the law has been used to protect companies from any liability in the past. In this podcast series, I will be explaining what Section 230 is, how it affects us, and what changes are being proposed. In doing so, I wish to shed a light on how the problems of the internet are not solely in the hands of social media giants and a 26-word long law, but all its users that make up our global community.

Contributors

Agent

Created

Date Created
2021-05

147748-Thumbnail Image.png

Twitter Patterns in the Politics of Social Mobilization: #BlackLivesMatter Case Study

Description

The role of technology in shaping modern society has become increasingly important in the context of current democratic politics, especially when examined through the lens of social media. Twitter is a prominent social media platform used as a political

The role of technology in shaping modern society has become increasingly important in the context of current democratic politics, especially when examined through the lens of social media. Twitter is a prominent social media platform used as a political medium, contributing to political movements such as #OccupyWallStreet, #MeToo, and #BlackLivesMatter. Using the #BlackLivesMatter movement as an illustrative case to establish patterns in Twitter usage, this thesis aims to answer the question “to what extent is Twitter an accurate representation of “real life” in terms of performative activism and user engagement?” The discussion of Twitter is contextualized by research on Twitter’s use in politics, both as a mobilizing force and potential to divide and mislead. Using intervals of time between 2014 – 2020, Twitter data containing #BlackLivesMatter is collected and analyzed. The discussion of findings centers around the role of performative activism in social mobilization on twitter. The analysis shows patterns in the data that indicates performative activism can skew the real picture of civic engagement, which can impact the way in which public opinion affects future public policy and mobilization.

Contributors

Created

Date Created
2021-05

131615-Thumbnail Image.png

Improving User Experience for College Admissions

Description

The Barrett Honors College website contains a lot of information that isn’t easily accessible by Honors Students. Many honors students have trouble finding the correct information they need. Important information is scattered all over the website making it difficult for

The Barrett Honors College website contains a lot of information that isn’t easily accessible by Honors Students. Many honors students have trouble finding the correct information they need. Important information is scattered all over the website making it difficult for honors students to find and understand the information they need. One example of this is the requirements for Lower and Upper Division credit. This website displays the upper and lower division credit needed for a student to graduate from the honors college via a noninteractive flowchart. Many high school seniors find it difficult to understand the mundane flowchart outlining the required honors credit that is required for graduating from Barrett at Arizona State University. Also, it is confusing for many transfer students with unique circumstances to determine the necessary requirements for them to graduate as a Barrett student.
These difficult flowcharts and confusing websites have a huge impact on a student’s ability to adequately receive the information they need and, in the end, can have a negative impact on their ultimate decision when deciding if Barrett is right for them. A better user experience can be a more effective way of displaying information to students. A better design that allows to user more interaction would allow for the user to better understand the information they are presented. Instead of a monotone flowchart displaying the requirements necessary to graduate with honors status, A web application where a user can input their information and get an output of the necessary requirements tailored to the unique circumstance would be more informative, useful, and easier to use. The web app would take information such as a student’s year, whether it be an incoming freshman or transfer student, and their current and previous course credit to determine the specific number of honors credits, The Human Event courses, and Thesis project required for this user to complete the requirements for Barrett Honors College. This application would give the user a better understanding of what is required of them and in turn lead to a better user experience.

Contributors

Agent

Created

Date Created
2020-05

Predicting Bitcoin Price Trend using Sentiment Analysis

Description

In this paper I defend the argument that public reaction to news headlines correlates with the short-term price direction of Bitcoin. I collected a month's worth of Bitcoin data consisting of news headlines, tweets, and the price of the cryptocurrency.

In this paper I defend the argument that public reaction to news headlines correlates with the short-term price direction of Bitcoin. I collected a month's worth of Bitcoin data consisting of news headlines, tweets, and the price of the cryptocurrency. I fed this data into a Long Short-Term Memory Neural Network and built a model that predicted Bitcoin price for a new timeframe. The model correctly predicted 75% of test set price trends on 3.25 hour time intervals. This is higher than the 53.57% accuracy tested with a Bitcoin price model without sentiment data. I concluded public reaction to Bitcoin news headlines has an effect on the short-term price direction of the cryptocurrency. Investors can use my model to help them in their decision-making process when making short-term Bitcoin investment decisions.

Contributors

Agent

Created

Date Created
2020-05

134809-Thumbnail Image.png

Analysis of the Aftereffects of Terror Attacks on Social Media

Description

Social media has become a direct and effective means of transmitting personal opinions into the cyberspace. The use of certain key-words and their connotations in tweets portray a meaning that goes beyond the screen and affects behavior. During terror attacks

Social media has become a direct and effective means of transmitting personal opinions into the cyberspace. The use of certain key-words and their connotations in tweets portray a meaning that goes beyond the screen and affects behavior. During terror attacks or worldwide crises, people turn to social media as a means of managing their anxiety, a mechanism of Terror Management Theory (TMT). These opinions have distinct impacts on the emotions that people express both online and offline through both positive and negative sentiments. This paper focuses on using sentiment analysis on twitter hash-tags during five major terrorist attacks that created a significant response on social media, which collectively show the effects that 140-character tweets have on perceptions in social media. The purpose of analyzing the sentiments of tweets after terror attacks allows for the visualization of the effect of key-words and the possibility of manipulation by the use of emotional contagion. Through sentiment analysis, positive, negative and neutral emotions were portrayed in the tweets. The keywords detected also portray characteristics about terror attacks which would allow for future analysis and predictions in regards to propagating a specific emotion on social media during future crisis.

Contributors

Created

Date Created
2016-12