Icon

TextMining_​MovieBoxOfficePrediction

Forecasting Box-Office Success of Movies with Plot Summaries
Predicting Based on BoW and Bit Vector or TF Predicting Based on LDA Forecasting Box-Office Success of Movies with Plot Summaries This workflow shows how to predict box-office success categories using only plot summaries (i.e., storylines):Read the data from the Excel file.Structure the data via Bag-of-Words and LDA approaches.Develop prediction model models to assess the superiority of methods and models. Credit: Dr. Dursun Delen, Oklahoma State University Word Cloud Visualization by Class Color by category (class)Training and test setBased on documentfrequencyExtract topics fromdocumentsPOS tagging, lemmatization, stop word, number, ... filteringtopic keywordsin a word cloudColor by category (class)Training and test setColor by category (class) SimplePreprocessing Category To Class Document Vector Color Manager Partitioning Column Filter Term Filtering DecisionTree Learner Decision TreePredictor Topic Extractor(Parallel LDA) Preprocessing Tag Cloud Color Manager Decision TreePredictor Category To Class Column Filter Partitioning Color Manager DecisionTree Learner Scorer (JavaScript) Read Data & Convert Scorer (JavaScript) Predicting Based on BoW and Bit Vector or TF Predicting Based on LDA Forecasting Box-Office Success of Movies with Plot Summaries This workflow shows how to predict box-office success categories using only plot summaries (i.e., storylines):Read the data from the Excel file.Structure the data via Bag-of-Words and LDA approaches.Develop prediction model models to assess the superiority of methods and models. Credit: Dr. Dursun Delen, Oklahoma State University Word Cloud Visualization by Class Color by category (class)Training and test setBased on documentfrequencyExtract topics fromdocumentsPOS tagging, lemmatization, stop word, number, ... filteringtopic keywordsin a word cloudColor by category (class)Training and test setColor by category (class) SimplePreprocessing Category To Class Document Vector Color Manager Partitioning Column Filter Term Filtering DecisionTree Learner Decision TreePredictor Topic Extractor(Parallel LDA) Preprocessing Tag Cloud Color Manager Decision TreePredictor Category To Class Column Filter Partitioning Color Manager DecisionTree Learner Scorer (JavaScript) Read Data & Convert Scorer (JavaScript)

Nodes

Extensions

Links