About Us

作者：

ABOUT US

We are students from The Hong Kong University of Science and Technology, this is an Digital Humanity Project about the most trending topic—NFT artwork. In this project, we have explored the social influence, aesthetic value and market value of NFT through several digital methods. Welcome to contact us if you have any question or suggestion!

 

Team Members:

Gloria Lu      lluan@connect.ust.hk

Wennie Lin    ylinen@connect.ust.hk

Frankie Tan    ytanay@connect.ust.hk

Jerry Yan      zyanbc@connect.ust.hk

Joanne Huang  qhuangbb@connect.ust.hk

Alvin Cao     xcaoam@connect.ust.hk

NFT

作者：

Sentiment Analysis

In this section, we will examine tweets related to one of the most popular NFT collections, Bored Ape Yacht Club. By analyzing public opinions of this collection, we can gain a better understanding of the public sentiment towards it.

The analysis will be conducted in the following steps:

  • Scrape the data about tweets that include “BoredApeYC”

  • Generate a word cloud of all the text

  • Divide the file into sections that are readable by the Nocode Function website

  • Classify the text into different sentimental categories and calculate the proportion of each category

  • Analyze the word cloud of each sentiment category and identify high-frequency keywords

Word Cloud of All Text

After cleaning and recoding the data, I generated a word cloud of the text. The resulting graph is shown below.

From the graph, we can see that the words frequently mentioned with BoredApeYC can be divided into the following categories:

  • Main accounts of NFT

  • Producers/Artists related to the BoredApeYC collection

  • Platform: OpenSea

  • Descriptive words: token, NFT, project

  • Sentimental word: love”


Sentiment Analysis by Categories

Most of the public does not have a clear emotional trend towards this collection. However, compared to a small group of people, the overall emotional direction is positive.

Sentiment Score Calculation

Next, I sorted all the tweets into three files based on the previously categorized types of emotions, and calculated the sentiment score for each tweet.

Steps

  • VaderSentiment
  • SentimentIntensityAnalyzer

Positive Tweets

Word Cloud of Positive Tweets

Most Frequent Words in positive tweets

Words such as “love”, “thank”, “great”, “best”, “amazing”, “happy”, and “awesome” suggest positive emotions or gratitude towards BAYC. Words such as “project”, “team”, and “gift” suggest expectations or eagerness to participate in this project. While frequent words like “leave”, “hope”, and “save” may be a little bit far from this subject, we guess it is a way of preaching. It can also prove that BAYC is popular among the public.

Why do people like BAYC?

Apart from quantitative analysis, we also conducted qualitative analysis on the tweets in this category. We propose that BAYC fans might treasure this collection because of its Investment Potential, Unique and Creative Artwork, and the good feelings it brings.

Negative Tweets

Word Cloud of Negative Tweets

Most Frequent Words in negative tweets

As for negative tweets, “miss” is the most frequently mentioned word, which indicates that people may generate negative attitudes because of missing certain opportunities or events. Words such as “project”, “chance”, and “need” imply that some people believe that BAYC needs some improvements in the future. 

Why do people don't like BAYC?

Sentiment Analysis

In this section, we will examine tweets related to one of the most popular NFT collections, Bored Ape Yacht Club. By analyzing public opinions of this collection, we can gain a better understanding of the public sentiment towards it.

The analysis will be conducted in the following steps:

  • Scrape the data about tweets that include “BoredApeYC”

  • Generate a word cloud of all the text

  • Divide the file into sections that are readable by the Nocode Function website

  • Classify the text into different sentimental categories and calculate the proportion of each category

  • Analyze the word cloud of each sentiment category and identify high-frequency keywords

Word Cloud of All Text

After cleaning and recoding the data, I generated a word cloud of the text. The resulting graph is shown below.

From the graph, we can see that the words frequently mentioned with BoredApeYC can be divided into the following categories:

  • Main accounts of NFT

  • Producers/Artists related to the BoredApeYC collection

  • Platform: OpenSea

  • Descriptive words: token, NFT, project

  • Sentimental word: love”


Sentiment Analysis by Categories

Most of the public does not have a clear emotional trend towards this collection. However, compared to a small group of people, the overall emotional direction is positive.

Sentiment Score Calculation

Next, I sorted all the tweets into three files based on the previously categorized types of emotions, and calculated the sentiment score for each tweet.

Steps

  • VaderSentiment
  • SentimentIntensityAnalyzer

Positive Tweets

Word Cloud of Positive Tweets

Most Frequent Words in positive tweets

Words such as “love”, “thank”, “great”, “best”, “amazing”, “happy”, and “awesome” suggest positive emotions or gratitude towards BAYC. Words such as “project”, “team”, and “gift” suggest expectations or eagerness to participate in this project. While frequent words like “leave”, “hope”, and “save” may be a little bit far from this subject, we guess it is a way of preaching. It can also prove that BAYC is popular among the public.

Why do people like BAYC?

Apart from quantitative analysis, we also conducted qualitative analysis on the tweets in this category. We propose that BAYC fans might treasure this collection because of its Investment Potential, Unique and Creative Artwork, and the good feelings it brings.

Negative Tweets

Word Cloud of Negative Tweets

Most Frequent Words in negative tweets

As for negative tweets, “miss” is the most frequently mentioned word, which indicates that people may generate negative attitudes because of missing certain opportunities or events. Words such as “project”, “chance”, and “need” imply that some people believe that BAYC needs some improvements in the future. 

Why do people don't like BAYC?

Subscribe
Subscribe