Frieze London 2018 (Part 2): Natural Language Processing

Over 150 galleries from 20+ countries usually participate in a for-profit art fair.However, Frieze has now become much more than just an art fair. “Frieze Week” has become a cultural entertainment week where people attend purely to spectate, there’s a sculpture park, and even the main auction houses host their mid-season contemporary sales to coincide with Frieze.The aim of this article is to better understand Frieze London 2018 by presenting the findings of my natural language processing analysis of 5.6k Instagram and 3.2k Twitter posts about the art fair.Please scroll down to view my analysis via interactive data visualizations!Data and MethodsThe official hashtag for the event was #frieze..Next, I used the Google Cloud Natural Language API to get the sentiment for each tweet.Finally, I used the gensim library’s Word2Vec model to get word-embeddings vectors for each word in the entire corpus of tweets in relation to the word “frieze”..Word2Vec is used to compute the similarity between words from a large corpus of text — Kavita Ganesan’s article is a great explanation.Once I had vectors for each word, I then used the scikitlearn library to perform principal component analysis (PCA) for dimensionality reduction and to plot the most similar words (nearest neighbours) to “frieze”.You can check my Kaggle kernel here for all the analysis for this post.Analyzing the postsIn this section, I present the findings of my natural language processing (NLP) analysis..Below, I report on the following three metrics:Sentiment analysis of the tweets per day;Word frequency and hashtag frequency analysis;The output of the Word2Vec model: Principal Component Analysis (PCA) and nearest neighbour analysis.Sentiment analysisThe sentiment for each tweet was calculated using Google’s Cloud NLP API..Principal Component Analysis is then used to reduce the dimensions of the Word2Vec space down to x and y coordinates.Importantly, Word2Vec is used to capture the similarity and relationships between words from the 9,000 tweets.. More details

Leave a Reply