Simple Science

Cutting edge science explained simply

# Computer Science # Social and Information Networks # Computers and Society

Political Conversations on Twitter in 2024

A look at how social media shapes political views in the upcoming election.

Hazem Ibrahim, Farhan Khan, Hend Alabdouli, Maryam Almatrooshi, Tran Nguyen, Talal Rahwan, Yasir Zaki

― 6 min read


Twitter's Role in 2024 Twitter's Role in 2024 Politics election. How tweets shape opinions ahead of the
Table of Contents

Social media has transformed the way people share opinions and engage in politics. With the upcoming U.S. Presidential Election in 2024, Twitter has become a major platform for political discussions. As millions of users tweet about their favorite Candidates and issues, it is essential to understand how these interactions shape political views. This study examines thousands of tweets to find out how political candidates and their supporters express their opinions online.

The Role of Social Media in Politics

Social media platforms are vital for sharing information and engaging voters, especially during election seasons. They allow politicians to communicate directly with the public and gain support for their ideas. But, there's a flip side: these platforms can also lead to division and misinformation. As people rally behind their chosen candidates, the potential for polarization increases. This is why understanding online political conversations is crucial for fostering healthy dialogue.

What is Stance Detection?

Stance detection is the process of figuring out whether a tweet supports, opposes, or remains neutral toward a specific topic or candidate. By analyzing tweets, researchers can gain insights into the political views of constituents and how these views change during critical events. This information is vital for politicians and social media companies seeking to promote constructive conversations and combat misinformation.

The Dataset

For this study, researchers collected data from Twitter related to the 2024 U.S. Presidential Election. They focused on tweets from political figures and their Replies. The data set included 1,235 tweets from major candidates and over 63,000 replies to these tweets, covering a wide range of political opinions. The study analyzed tweets from May 1, 2024, to November 1, 2024, so they could see how political views evolved over time.

Who Were the Major Candidates?

The study focused on candidates from the two main political parties: Democrats and Republicans. The main figures included Joe Biden, Kamala Harris, Tim Walz from the Democratic Party, and Donald Trump and JD Vance from the Republican Party. Each candidate had their own unique approach to framing their tweets, and the research aimed to uncover these differences.

How Were Tweets Classified?

Researchers used advanced language models to help categorize the tweets. They specifically looked for five ideological positions:

  1. Pro-Democrat (supporting Democrats)
  2. Anti-Republican (criticizing Republicans)
  3. Pro-Republican (supporting Republicans)
  4. Anti-Democrat (criticizing Democrats)
  5. Neutral (no clear stance)

By utilizing these classifications, the researchers could better understand how each candidate positioned themselves and how their supporters interacted with their tweets.

Findings on Candidate Tweets

When examining the tweets from Democratic candidates, around 48.1% were in support of the Democratic Party, while 26.4% criticized Republicans, and 25.5% were neutral. In comparison, Republican candidates had a different approach: 40.2% of their tweets supported their party, while 40.6% criticized Democrats. Statistically speaking, Republicans were found to tweet more about criticizing Democrats than vice versa.

Replies to Candidate Tweets

Looking into the replies to candidate tweets, an interesting trend emerged. Most replies to Democratic candidates were criticisms of the Democratic Party, with 69.2% classified as Anti-Democrat. However, only 31.7% of replies to Republican candidates were classified as Anti-Republican. This pattern suggests that Republican supporters were more vocal in replying to both party tweets.

Engagement with Tweets

Engagement levels for different types of replies also varied. For Republican candidates, replies supporting them received more engagement overall, while replies criticizing Democratic candidates were less engaging. This raises questions about the motivations behind these interactions and whether factors like "muting" habits or automated bots were at play.

The Impact of Major Political Events

The study also looked at how major political events in the lead-up to the election affected the tone and nature of tweets. They focused on three key events:

  1. The first presidential debate between Biden and Trump
  2. A Supreme Court ruling on presidential immunity
  3. Trump’s attempted assassination

Researchers used a method called regression discontinuity in time to analyze the impact of these events on tweeting behavior.

The First Presidential Debate

After the debate, a drop in Anti-Democrat tweets and an increase in Pro-Republican tweets were noted. This revealed differing reactions from party supporters based on their ideological alignments.

The Supreme Court Ruling

Following the ruling, there was a significant rise in Pro-Republican tweets and a drop in Anti-Democrat tweets. Meanwhile, Democrats saw a major increase in Anti-Republican tweets, alongside a decrease in Pro-Democrat tweets.

Trump's Attempted Assassination

In response to Trump’s attempted assassination, both Republican and Democrat tweets shifted significantly. Democrats reduced their Pro-Democrat tweets while Republicans ramped up their Pro-Republican tweets, demonstrating a notable influence of this high-profile event on public discourse.

Key Patterns

Across all three events, a consistent pattern emerged: there was a marked increase in both Anti-Republican and Pro-Republican replies, while Pro-Democrat and Anti-Democrat replies decreased significantly. This indicates that conversations focused more on support or criticism of Trump and the Republican Party than on Democrat-related discussions.

Limitations of the Study

Despite the wealth of data analyzed, the study acknowledges several limitations. The dataset does not encompass all political tweets, meaning the findings only represent a sample of the discourse. This limitation must be kept in mind when interpreting the results.

Future Research Directions

Future work can explore how bot accounts influence political ideologies on social media platforms. Researchers can also delve into the evolving political landscape beyond the two-party system, examining third-party candidates and their ideologies. Additionally, it could be insightful to collect and analyze sentiments on other sites like TikTok, BlueSky, or TruthSocial, since each platform caters to different users and demographics.

Ethical Considerations

All data used in this study were publicly available, and the researchers ensured that informed consent was obtained from human annotators who validated the model outputs. With ethical research practices in place, the team aimed to maintain integrity in their analysis.

Conclusion

Analyzing political discourse on Twitter offers important insights into how public opinions are shaped in the lead-up to elections. Whether it's through candidates’ tweets or their supporters’ replies, understanding these dynamics can help inform strategies for healthy political discussions. As the election approaches, keeping a close eye on social media conversations will be critical for comprehending the evolving political landscape. So grab your popcorn, and let's see how this political drama unfolds online!

Original Source

Title: Analyzing political stances on Twitter in the lead-up to the 2024 U.S. election

Abstract: Social media platforms play a pivotal role in shaping public opinion and amplifying political discourse, particularly during elections. However, the same dynamics that foster democratic engagement can also exacerbate polarization. To better understand these challenges, here, we investigate the ideological positioning of tweets related to the 2024 U.S. Presidential Election. To this end, we analyze 1,235 tweets from key political figures and 63,322 replies, and classify ideological stances into Pro-Democrat, Anti-Republican, Pro-Republican, Anti-Democrat, and Neutral categories. Using a classification pipeline involving three large language models (LLMs)-GPT-4o, Gemini-Pro, and Claude-Opus-and validated by human annotators, we explore how ideological alignment varies between candidates and constituents. We find that Republican candidates author significantly more tweets in criticism of the Democratic party and its candidates than vice versa, but this relationship does not hold for replies to candidate tweets. Furthermore, we highlight shifts in public discourse observed during key political events. By shedding light on the ideological dynamics of online political interactions, these results provide insights for policymakers and platforms seeking to address polarization and foster healthier political dialogue.

Authors: Hazem Ibrahim, Farhan Khan, Hend Alabdouli, Maryam Almatrooshi, Tran Nguyen, Talal Rahwan, Yasir Zaki

Last Update: 2024-11-28 00:00:00

Language: English

Source URL: https://arxiv.org/abs/2412.02712

Source PDF: https://arxiv.org/pdf/2412.02712

Licence: https://creativecommons.org/licenses/by/4.0/

Changes: This summary was created with assistance from AI and may have inaccuracies. For accurate information, please refer to the original source documents linked here.

Thank you to arxiv for use of its open access interoperability.

More from authors

Similar Articles