A method based on Interactive Evolutionary Computation and fuzzy logic for increasing the effectiveness of advertising campaigns
| Autor: | Oscar Castillo, Alejandra Mancilla, Quetzali Madera, Mario García-Valdez |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Information Systems and Management
Computer science Interactive evolutionary computation 02 engineering and technology Machine learning computer.software_genre Fuzzy logic Theoretical Computer Science Advertising campaign Artificial Intelligence Evolutionary music Genetic algorithm 0202 electrical engineering electronic engineering information engineering Fitness function business.industry 05 social sciences 050301 education Evaluation function Computer Science Applications Control and Systems Engineering 020201 artificial intelligence & image processing Artificial intelligence business 0503 education computer Software Word (computer architecture) |
| Zdroj: | Information Sciences. 414:175-186 |
| ISSN: | 0020-0255 |
| DOI: | 10.1016/j.ins.2017.06.001 |
| Popis: | Optimization of advertising texts is aimed at increasing the number of users who take notice of the ad. The work presented in this paper proposes a method to optimize advertising texts through Interactive Evolutionary Computation and fuzzy logic. This is done by utilizing user preferences for word combinations to build a fitness function. After several generations, the Interactive Evolutionary Computation algorithm should produce a version of the advertising text that exhibits an increase in efficacy (as judged by the subjective evaluation function used for its evolution). To demonstrate the efficacy of the evolved texts, they are compared against word combinations chosen by experts in marketing and related fields. Recognition, recall, and persuasion tests were performed to evaluate the efficacy of the proposed method. The obtained results show that Interactive Evolutionary Computation can be used to increase the efficacy of an advertising text. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect