ActRec: A Word Embedding-based Approach to Recommend Movie Actors to Match Role Descriptions
Ai-Ni Lee, Kuan-Ying Chen, Cheng–Te Li · 2020
In this work, we propose a novel recommendation problem, actor recommendation (ActRec), based on unstructured text data for the movie industry. Given the text description of a role, we generate a ranking list of actors such that the most proper actors for the role-playing can be at top positions. We propose a word embedding-based approach to solve the ActRec problem. In addition, we compile a multi-source data from Wikipedia, Google Search, and PTT online forum. Experimental results show the promising performance of our method, which encourages future effort on ActRec.