{"id":1002,"date":"2020-11-14T12:23:49","date_gmt":"2020-11-14T09:23:49","guid":{"rendered":"https:\/\/persona.qcri.org\/blog\/?p=1002"},"modified":"2021-03-21T14:25:16","modified_gmt":"2021-03-21T11:25:16","slug":"how-suitable-are-artificially-generated-facial-pictures-in-data-driven-personas","status":"publish","type":"post","link":"https:\/\/persona.qcri.org\/blog\/how-suitable-are-artificially-generated-facial-pictures-in-data-driven-personas\/","title":{"rendered":"How suitable are artificially generated facial pictures in data-driven personas?"},"content":{"rendered":"

In a previous post, we analyzed <\/span>the demographic Bias in Artificially Generated Facial Pictures<\/a> <\/span>that raised a concern that the generated images might not fairly represent all demographic groups.<\/span><\/p>\n

In this post, we discuss if these artificially generated pictures are good enough for use in personas profiles for real-world systems and applications,\u00a0 which are highly dependent on images for the personas. One of the key aspects of generating personas using a data-driven approach is to be able to represent the persona profile with a matching picture.<\/span><\/p>\n

<\/span><\/p>\n

Artificial image generation (AIG) provides novel opportunities for a wide range of applications. For example, the Verge has published a tech article about one of the <\/span>studies that use AI to generate endless fake faces using Generative Adversarial Network (GAN)<\/a><\/span>. However, despite the far-reaching interest in AIG among academia and across industries, there is scant research on evaluating the suitability of the generated images for practical use in deployed systems.<\/span><\/p>\n

This means that the quality and impact of the artificial images on user perceptions are often neglected and lacking user studies of their deployment in real systems. This area of evaluation is an overlooked but critical area of research, as it is the \u2018final step\u2019 of deployment that actually determines if the quality of the AIG is good enough for real systems. Therefore, the impact of AIG on user experience (UX) and design applications is a largely unaddressed field of study.\u00a0<\/span><\/p>\n

The AIG impact can add an enhancement and improves the user experience for the highest matching persona picture, which can be useful for various applications. Such applications included, for example, designing a chatbot, where the idea is to make the bot more engaging and close to the human. Therefore, using the best persona image that describes the bot is of great value.\u00a0 <\/span>For exa<\/span>mple, which one of the pictures below do you feel most comfortable talking with when dealing with a chatbot? The chatbot in PictureA or B? For many folks, it’s much more realistic to speak with a chatbot who looks like the character in Picture B.<\/span><\/p>\n

\"A
Picture A: A Very Artificial Personas for a ChatBot.<\/figcaption><\/figure>\n
\"A
Picture B: A Realistic Persona Generated Artificially.<\/figcaption><\/figure>\n

There are other domains that can benefit from the best matching picture with the APG, including Marketing and Advertising, Ecommerce sites, Retail brochures, and virtual agents.<\/span><\/p>\n

Most importantly, the use of AIG is generally free of copyright restrictions and can allow for a wide range of <\/span>demographic diversity<\/span><\/a> (age, gender, ethnicity). The challenge is how to reach a certain level of agreement that the generated pictures are\u00a0 \u2018good enough\u2019 for real-life applications.\u00a0\u00a0<\/span><\/p>\n

In this research, the goal is to evaluate artificially generated pictures across multiple dimensions for deployment in data-driven personas. To achieve this evaluation task, we apply a pre-existing method for generating the persona profiles and then evaluate the results for user perceptions. This evaluation can be considered as a practical design and implementation of AIG.<\/span><\/p>\n

Overall in this study, we measure the:\u00a0<\/strong><\/p>\n