Browsing UA Faculty Research by Journal
Now showing items 1-2 of 2
Transparency and accountability in AI decision support: Explaining and visualizing convolutional neural networks for text informationProliferating applications of deep learning, along with the prevalence of large-scale text datasets, have revolutionized the natural language processing (NLP) field, thereby driving the recent explosive growth. Nevertheless, it is argued that state-of-the-art studies focus excessively on producing quantitative performances superior to existing models, by playing "the Kaggle game." Hence, the field requires more effort in solving new problems and proposing novel approaches and architectures. We claim that one of the promising and constructive efforts would be to design transparent and accountable artificial intelligence (AI) systems for text analytics. By doing so, we can enhance the applicability and problem-solving capacity of the system for real-world decision support. It is widely accepted that deep learning models demonstrate remarkable performances compared to existing algorithms. However, they are often criticized for being less interpretable, i.e., the "black box." In such cases, users tend to hesitate to utilize them for decision-making, especially in crucial tasks. Such complexity obstructs transparency and accountability of the overall system, potentially debilitating the deployment of decision support systems powered by AI. Furthermore, recent regulations are emphasizing fairness and transparency in algorithms to a greater extent, turning explanations more compulsory than voluntary. Thus, to enhance the transparency and accountability of the decision support system and preserve the capacity to model complex text data at the same time, we propose the Explaining and Visualizing Convolutional neural networks for Text information (EVCT) framework. By adopting and ameliorating cutting-edge methods in NLP and image processing, the EVCT framework provides a human-interpretable solution to the problem of text classification while minimizing information loss. Experimental results with large-scale, real-world datasets show that EVCT performs comparably to benchmark models, including widely used deep learning models. In addition, we provide instances of human-interpretable and relevant visualized explanations obtained from applying EVCT to the dataset and possible applications for real-world decision support.
Uncovering the effects of digital movie format availability on physical movie salesThe impact of multi-channel technology-enabled digital goods on the sales of the physical counterpart faces uncertainty in the electronic commerce domain. We address the issue empirically by identifying the effect of the availability of digitally-delivered movies on physical DVD movie sales. Unique to our study is our interest in not only purchased digital goods but rented digital goods as well. We construct a robust panel dataset consisting of movie data collected from Amazon and Barnes and Noble on the same day for every movie observed. A key feature of our dataset is the multi-channel availability of digital purchase and digital rental movie formats at Amazon. Our results show that the availability of the digital purchase format does not have a significant effect on DVD sales. Surprisingly, the availability of the digital rental format is associated with a significant reduction in DVD sales. The results imply that a product substitution effect may be occurring between the digital rental and the physical DVD purchase of the same movie. We conduct robustness tests to show under which conditions the effect is greatest. Our results also provide practical implications to inform strategies regarding movie format release windows.