Matching Items (6)
Filtering by
- Creators: Department of Information Systems
Description
This project analyzes the tweets from the 2016 US Presidential Candidates' personal Twitter accounts. The goal is to define distinct patterns and differences between candidates and parties use of social media as a platform. The data spans the period of September 2015 to March 2016, which was during the primary races for the Republicans and Democrats. The overall purpose of this project is to contribute to finding new ways of driving value from social media, in particular Twitter.
ContributorsMortimer, Schuyler Kenneth (Author) / Simon, Alan (Thesis director) / Mousavi, Seyedreza (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
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 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.
ContributorsDavis, Matthew William (Author) / Liu, Huan (Thesis director) / Nazer, Tahora H. (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
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 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.
ContributorsHarikumar, Swathikrishna (Author) / Davulcu, Hasan (Thesis director) / Bodford, Jessica (Committee member) / Computer Science and Engineering Program (Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Twitter is one of the most powerful communication tools ever created. There are over 1.3 billion registered Twitter users (Smith, 2016). 100 million daily people actively use Twitter every day. 6,000 tweets are tweeted every second. Communication has never been so abundant, public, and chronicled. Not only is there a gigantic population to market to, but also a wealth of information about that population to record and draw insights from. However, many companies' Twitter accounts fail to generate popular posts on a regular basis. The content that they produce is ineffective and uninteresting. In my opinion, these companies are failing to take advantage of a huge opportunity. I decided to dive into the Twitter accounts of some of my favorite companies to see what they were doing wrong and how they could improve. My thesis investigates 18 different company Twitter accounts from four different industries: Athletic Apparel, Technology, Online Entertainment, and Car Manufacturing. I pulled 200 tweets from each company and cleaned and organized the data into an Excel spreadsheet. I investigated how certain variables impacted tweet popularity across the four industries. First, I looked at tweet format to determine whether posts, retweets, or replies were the best format. Then, I analyzed how different elements of a tweet's content could impact the tweet's popularity. Specifically, I looked at the effects of including links, hashtags, and questions into the tweet. Next, I tried to determine the optimal tweet length for each industry. And finally, I compared each industry's tweet sentiment preferences. I then summarized my findings into a series of recommendations for companies to improve their tweet popularity.
ContributorsFrame, Christopher James (Author) / Clark, Joseph (Thesis director) / Jenkins, Anthony (Committee member) / Department of Information Systems (Contributor) / Department of Finance (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
As online media, including social media platforms, become the primary and go-to resource for traditional communication, news and the spread of information is more present and accessible to consumers than ever before. This research focuses on analyzing Twitter data on the ongoing Russian-Ukrainian War to understand the significance of social media during this period in comparison to previous conflicts. The significance of social media and political conflict will be examined through Twitter user analysis and sentiment analysis. This case study will conduct sentiment analysis on a random sample of tweets from a given dataset, followed by user analysis and classification methods. The data will explore the implications for understanding public opinion on the conflict, the strengths and limitations of Twitter as a data source, and the next steps for future research. Highlighting the implications of the research findings will allow consumers and political stakeholders to make more informed decisions in the future.
ContributorsBlavatsky, Sofia (Author) / Hahn, Richard (Thesis director) / Sirugudi, Kumar (Committee member) / Inozemtseva, Julia (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Department of Information Systems (Contributor)
Created2023-05
Description
Basketball has evolved and is continuing to evolve in parallel with media and communication. The 21st century bears witness to the digitization of basketball, media, and communication with the advent of social media. Arguably the most esteemed professional basketball league in the world, the National Basketball Association (NBA) observes fans and players alike conversing about the game through social media platforms available across the world. One of the most popular platforms, Twitter, enables anyone with a computer to write a textual post known as a “tweet” that can be made viewable to the public. The Twitter landscape holds a trove of data and information including “sentiment” for NBA teams to analyze with the goal of improving the success of their team from a managerial perspective. Two aspects this paper will examine are fan engagement and revenue generation from the perspective of several franchises in the NBA. The purpose of this research is to explore and discover if key measures of performance including both the number of points scored in a game and the game outcome either being a win or a loss, and the location of a game being won either at home or away on the road influence fan Twitter sentiment and if there is a correlation between fan Twitter sentiment and game attendance. The statistical computing tool RStudio in combination with data compiled from online databases and websites including Basketball Reference, Wikipedia, ESPN, and Statista are employed to execute two t-tests, two analysis of variance (ANOVA) tests, and one correlation test. The results indicate there is a significant difference in fan Twitter sentiment between high-scoring games and low-scoring games, between game wins and losses, among games being won at home versus away on the road, and there is no conclusion that can be made regarding any existing correlation between fan Twitter sentiment and game attendance.
ContributorsKwan, Matthew (Author) / McIntosh, Daniel (Thesis director) / Eaton, John (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Department of Information Systems (Contributor)
Created2022-05