CSE564 — Final Project Proposal

Author: Kai-Chieh Huang (112676186), Hsien-Yi Liu (112675266)

Background

With the rise of social media, such as Facebook and Twitter, which creates real-time information delivery and strong social networking, have received significant attention from the public and allowed us to better develop our understanding of the influence of social media on daily life.

According to many studies, we also discovered the huge impact of social media on the economy. Through reshaping the news landscape and revolting the power of news dissemination, social media becomes an unremarkable factor when discussing the financial market. Among them, opinion leaders play an important role. They used to have lots of followers and reviews which could transfer to the huge amount of voice on social media and caused influence on the related field.

The most famous story is how Mr. Trump utilized Twitter to influence the 2016 US election. With the features of Twitter, real-time and short, Mr. Trump’s team successfully reached their goal of connecting with voters. Obsessed with the flow of information on the social media, Twitter becomes the one of the potent weapon for Mr. Trump to win the election.

Therefore, we tried to imagine if Mr. Trump could bring those effects on election, maybe there could be other similar impacts on different areas.

Allocating problems with datasets

As we all know, President Trump tweets frequently on Twitter. We believe that these messages will influence the country in many ways, especially on the economy. To increase the diversification of our research, we decided to analyze the influence by President Trump from different financial aspects.

First of all, stock markets occupy the principal role in the economy. As a result, we develop one of our problems as “Could President Trumps’ tweets bring impact on the stocks’ trend”. In our research, two main stock markets indexes would be taken into account, S&P500 and ETF. Tracking the 500 largest U.S companies, S&P 500 could be the most accurate quantifier of the U.S. economy by reflecting the biggest companies risks and returns. To improve the credibility and reliability of our research, we will make use of the Exchange-Trends Fund (ETF) as the control group. Because the ETF could be seen as an extension of S&P 500, we believed they would create some similar results from President Trumps’ tweet.

Apart from the stock market, the US dollar also plays an important role in the currency markets. Once understanding that there are no practical boundaries for social media, we know that it’s interesting to analyze the connection between them. Therefore, our second question would try to find the relationship between currency with President Trump tweets.

To diversify our research, we will take other datasets into account which may be influenced by President Trump’s tweets, like oil price and housing price, etc. During the research, we will mainly focus on his presidential period, and hope to conceive some clues and relationships between his words and datasets to support our assumption.

Approach

Process of sentiment analysis

Fig 1, Example of calculate sentiment score

Understanding people’s emotions is essential for developing research about social media, because there is no voice in the world of social media but text instead. Through extracting the polarity of the words, we could stimulate the reviewers’ reflection after reading the review. Consequently, we must apply sentiment analysis in our research.

To fully grasp the sentiment behind the text, we utilize the famous sentiment analysis dictionary called SentiwordNet to discover the polarity of tweets from Mr. Trump. The Fig 1 in the above, is showing how we apply sentiment analysis in our research. First, we will remove the stop words like are, to, with, in, and the, etc which is hard to understand the emotion behind the words. Then, we will use the dictionary from SentiWordNet to calculate the sentiment score. Finally, we achieved our goal and could start to find the relationship between the social media and other datasets.

Dashboard Layout Design

Fig 2, Dashboard Diagram

Above figure (Fig 2) is how we will design our dashboard layout. We can split this dashboard into four parts.

For the top left part, it will be a timeline graph which will display all President Trump’s recent tweets by its datetime sequentially. Users can scroll through this graph to see what he has tweeted before and click on each message to view the content and see its relationship with other information at that moment.

For the bottom left line chart, it is used to display information that is related to President Trump’s tweet at the same datetime, which includes stock price, house price, and USD exchange rate. Users can choose to see which line chart they prefer, and the chart will be scrolled synchronously with the above timeline graph.

At the top right corner, when a user clicks on a tweet on the timeline graph, the details of the clicked tweet will display here, like message content, likes, comments (only amount will display), and sentiment score. Also, the exact number of those related line chart values will pop up here as well, which can provide users with a clear view of how the tweet is related to each dataset.

The last one on the bottom right, here is to show the analytic of each dataset. If the user wants to know more detail separately, the user can select different types of visualization method here like pie charts, MDS, PCA, etc, and control multiple attributes to learn more from it.

Reference

[1] Stock Market Reactions to Presidential Social Media Usage: Evidence from Company-Specific Tweets, Qi Ge, Alexander Kurov, Marketa H. Wolfe [ link ]

[2] How Twitter is Changing the Nature of Financial News Discovery, Mark Dredze , Prabhanjan Kambadur, Gary Kazantsev, Gideon Mann, Miles Osborne [ link ]

[3] How Trump Reshaped the Presidency in Over 11,000 Tweets, Michael D. Shear, Maggie Haberman, Nicholas Confessore, Karen Yourish, Larry Buchanan and Keith Collins [ link ]

[4] Underlying Socio-political Processes Behind the 2016 US Election, John Bryden, Eric Silverman [ link ]