Aller au contenu
Hub Nexus

What They Measured (And How They Got the Data)

Version2
Mis à jour

Auteurgor

Quelque chose à améliorer ? Proposez une modification.

Soutien

Cette page est publique.

Intro

Section of this node - https://www.hubnx.com/nodes/200b2ec1-37ec-4be6-adc7-57838917d255/sections/c1677a39-c987-48cd-8d2f-c896a09eff0a

In this node we would discuss how researchers gathered the data, the strategy they used, and what exactly did they mesaure to determine the sucess of movies? We would make sure to highlight the important details, but will not complicate it!

Collection of Data

The researchers picked 24 movies released between November 2009 and February 2010 - including big names like Avatar, The Blind Side, and Twilight: New Moon.

They collected:

  • 2.89 million tweets over 3 months
  • Data using the Twitter Search API
  • Keywords = movie titles
  • Time range = 7 days before release → 14 days after

Then they measured two key features:

1. Tweet-Rate

How many tweets per hour each movie got, before and after release.

Example: “Twilight: New Moon” had over 1,300 tweets/hour before opening.
“Transylmania”? Just 2.75/hour.

This variable alone turned out to be incredibly predictive.

2. Sentiment

They built a sentiment classifier using Mechanical Turk.

  • 3,000 tweets were labeled as Positive / Negative / Neutral
  • This became training data for a Naive Bayes classifier
  • It was then used to analyze sentiment trends for all 2.8M tweets

They also collected box office performance data and number of theaters released in, to add more context.

Cinéma & TVLogiciel

Dans ces publicationsPredicting the Future With Social Media - Sitaram Asur & Bernardo A. Huberman

LanguesEnglish

Licence : Tous droits réservés

Vues

Commentaires

Spinner Logo

À lire ensuite

The Machine Learning Model
Version: 2
In this node would look at which Machine Learning model was used during the research, even though that might sound scary or complicated, in reality it is actually not a complex method. We would concisely go over the models tested, a short node about the key methods used.
Why This Still Matters (and How You Can Build on It Today)
Version: 2
Final words about the research, the importance of project and how you can build similar project yourself!
What They Found (And What It Means for ML in the Real World)
Version: 2
We would discuss the findings of research and impact, new perception that it led to in Machine Learning sphere.
The Research That Predicted Movie Success with Twitter Data
Version: 4
Introductory node of a series of nodes that are part of research 'Predicting the Future With Social Media' performed by Sitaram Asur & Bernardo A. Huberman, this is a example of usage of nodes and platform for research purposes. All the sources and links are provided to the original paper and can be found in 'Sections'.
Why Undergrad Research Isn’t Just for PhDs, It’s a Skill Accelerator
Version: 1
Benefits of research position as an undergraduate, steps on getting to that position with no/low experience.
The Internet Gave Us Infinite Reach - But It Didn’t Teach Us How to Be Seen
Version: 1
The importance of visibility and chasing the opportunity in current digital world, few short tips on how to be seen and heard.