Paper Number
2322
Paper Type
Short Paper
Abstract
There is a near overflow of presentation slides on digital platforms, such as SlideShare.net, with 40 million. This presents a challenge in assessing their projected impact due to its high complexity and required expertise. We propose a novel approach using machine learning techniques to predict presentation slide audience reach. We crawled a unique dataset of over 8000 slides and extracted relevant attributes. A model was trained where we are the first to employ both numerical and textual inputs. Initial results with an R² value of 0.579 suggest that the audience reach of presentation slides can be automatically evaluated. Our findings contribute to the current understanding of the assessment of online documents, introducing possibilities for further research, such as focusing on domain-specific applications and incorporating them as tools for decision support in content management systems on sharing platforms.
Recommended Citation
Meier, Alexander; Rietsche, Roman; and Blohm, Ivo, "An AI Approach for Predicting Audience Reach of Presentation Slides" (2024). ECIS 2024 Proceedings. 9.
https://aisel.aisnet.org/ecis2024/track04_impactai/track04_impactai/9
An AI Approach for Predicting Audience Reach of Presentation Slides
There is a near overflow of presentation slides on digital platforms, such as SlideShare.net, with 40 million. This presents a challenge in assessing their projected impact due to its high complexity and required expertise. We propose a novel approach using machine learning techniques to predict presentation slide audience reach. We crawled a unique dataset of over 8000 slides and extracted relevant attributes. A model was trained where we are the first to employ both numerical and textual inputs. Initial results with an R² value of 0.579 suggest that the audience reach of presentation slides can be automatically evaluated. Our findings contribute to the current understanding of the assessment of online documents, introducing possibilities for further research, such as focusing on domain-specific applications and incorporating them as tools for decision support in content management systems on sharing platforms.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.