VAST 2013 Mini-Challenge 1: Box Office VAST - Team VADER

نویسندگان

  • Yafeng Lu
  • Feng Wang
چکیده

VAST 2013 Mini-Challenge 1 was a rolling competition in which participants would submit a set of weekly predictions for movie revenue and viewer rating. This was a closed world contest in which contestants were provided with a set of Twitter indices, bitly links, and access to the Internet Movie Database. In order to facilitate these predictions, we have created a web-deployable system that combines predictive techniques (multiple linear regression), data mining (sentiment analysis), and interactive visualizations for predicting the opening weekend gross and viewer rating scores of upcoming movies. Taking use this system with human in the loop, we got 4 times top predictor in 11 entries of submission.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Author manuscript, published in "VAST Challenge n°1 (2013)"

CinemAviz is a visualization tool for the exploration of the Imdb database. It consists of a variant of a scatterplot matrix— with different cell views—and a prediction panel to estimate the user rating and opening week box office of released movies.

متن کامل

Enhancing the "think loop process" with consistent interactions: VAST 2012 Mini Challenge 1 award: Honorable mention for good interaction techniques

The 2012 VAST Mini-Challenge 1 presented in excess of 158 million data points for analysis. The data consisted of network events from Bank of Money, a large organization whose branches spanned the entirety of fictional BankWorld, as well as the assets generating the events. Two network event datasets were used to analyze the network’s state and determine what anomalies could be affecting it. Th...

متن کامل

Data ingestion and evidence marshalling in Jigsaw VAST 2010 Mini Challenge 1 award: Good support for data ingest

This article describes the sense-making process we applied to solve the VAST 2010 Mini Challenge 1 using the visual analytics system Jigsaw. We focus on Jigsaw’s data ingest and evidence marshalling features and discuss how they are beneficial for a holistic sense-making experience.

متن کامل

VAST 2010 Challenge: Arms dealings and pandemics

1 The 5 VAST Challenge consisted of three mini-challenges that involved both intelligence analysis and bioinformatics. Teams could solve one, two or all three mini-challenges and assess the overall situation to enter the Grand Challenge. Mini-challenge one involved text reports about people and events giving information about arms dealers, situations in various countries and linkages between di...

متن کامل

City sentinel - VAST 2011 mini challenge 1 award: "Outstanding integration of computational and visual methods"

We present City Sentinel, an in-house built visual analytic software capable of handling a large collection of textual documents by combining diverse text mining and visualization tools. We applied this tool for the Vast Challenge 2011, Mini Challenge 1 over millions of tweet messages. We demonstrate how City Sentinel aided the analyst in retrieving the hidden information from the tweet message...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013