Using classified text and deep learning algorithms to identify entertainment risk and provide early warning
Deep learning is used to identify specific, potential entertainment risks to an enterprise while such risks before the enterprise commits large sums of money to a project. The system involves mining and using existing classifications of data (e.g., from a database of previously successful book and film franchises) to train one or more deep learning algorithms, and then examining a proposed entertainment document with the trained algorithm, to generate a scored output that will enable enterprise personnel to be alerted to risks and take action in time to prevent the risks from resulting in harm to the enterprise.
1. A method of using classified text and deep learning algorithms to identify entertainment risk and provide objective assessment comprising:
obtaining one or more training datasets for textual data corresponding to one or more entertainment classifications, wherein said entertainment classifications comprise one or more genres of interest;
training one or more deep learning algorithms using said one or more training datasets;
obtaining one or more proposed entertainment documents as test data;
applying said one or more deep learning algorithms to said one or more entertainment documents to determine and report how accurately said one or more entertainment documents is representative of said one or more genres of interest;
enabling a user with a graphical user interface to determine if said determination of representativeness is a false positive or a true positive and to what degree; and
enabling said user to re-train said one or more deep learning algorithms if said determination of representativeness is a false positive or a true positive.
2. The method of claim 1 , wherein said one or more deep learning algorithms is a framework for natural language processing of text.
3. The method of claim 1 , wherein said one or more deep learning algorithms is a recurrent neural network with a multiplicity of layers and various features, including but not limited to long short-term memory or gated recurrent units.
4. The method of claim 1 , wherein the one or more deep learning algorithms have been trained with different classifiers using previously classified data sourced and provided by a subject matter expert to become models for specific genres of interest.
5. The method of claim 1 , wherein each one of said one or more deep learning algorithms has also been trained with one or more datasets unrelated to the genres of interest.
6. The method of claim 5 , wherein each one of said one or more deep learning algorithms scores the one or more proposed entertainment documents for accuracy with the deep learning model classification of the data and provides a report.
7. The method of claim 6 , wherein said report comprises providing scores and related data to one or more designated users.
8. The method of claim 7 , wherein said report may be limited to scores which surpass a specified threshold associated with each of said one or more deep learning algorithms.
9. The method of claim 1 , wherein said one or more training datasets is a positive training set comprising commercially successful books or movies, and a negative training set comprising text unrelated to books or movies, but which may include books that were published, or films that were made, but which were unsuccessful to one degree or another.
10. A method of using classified text and deep learning algorithms to identify entertainment risk and provide objective assessment comprising:
obtaining one or more training datasets for textual data corresponding to one or more entertainment classifications, wherein said entertainment classifications comprises one or more genres of interest;
training one or more deep learning algorithms using said one or more training datasets;
obtaining a proposed entertainment document, wherein said entertainment document comprises a book or a movie script;
applying said one or more deep learning algorithms to said entertainment document to generate success scores for each of said one or more genres of interest; and
reporting said success scores for each of said one or more genres of interest.
11. The method of claim 10 , further comprising retraining said one or more deep learning algorithms if said any one of said success scores for said one or more genres of interest is a false positive.
12. The method of claim 11 , wherein said false positive determination is performed by a user through a graphical user interface.
13. The method of claim 11 , wherein said one or more training datasets is a positive training set comprising commercially successful books and movies and a negative training set comprising books that were published, or films that were made, but which were unsuccessful to one degree or another.
14. A method of using classified text and deep learning algorithms to identify entertainment risk and provide objective assessment comprising:
obtaining one or more training datasets for textual data corresponding to one or more entertainment classifications, wherein said entertainment classifications comprise one or more genres of interest;
training one or more deep learning algorithms using said one or more training datasets;
obtaining a proposed entertainment document;
applying said one or more deep learning algorithms to said entertainment document to generate prediction if said entertainment document is representative of said one or more genres of interest;
determining if said prediction for one of said one or more genres of interest is a false positive or a true positive; and
re-training said one or more deep learning algorithms if said prediction for said one or more genres of interest is a false positive.
15. The method of claim 14 , wherein said one or more deep learning algorithms is a recurrent neural network with a multiplicity of layers and various features, including but not limited to long short-term memory or gated recurrent units.
16. The method of claim 14 , wherein each one of said one or more deep learning algorithms has also been trained with one or more datasets unrelated to the genres of interest.
17. The method of claim 14 , wherein each one of said one or more deep learning algorithms scores the data for accuracy with the deep learning model classification of the data.
18. The method of claim 17 , wherein said prediction comprises scores and related data.
19. The method of claim 14 , wherein said one or more training datasets is a positive training set comprising commercially successful books and movies and a negative training set comprising books that were published, or films that were made, but which were unsuccessful to one degree or another.