{"id":645,"date":"2023-04-22T11:39:44","date_gmt":"2023-04-22T08:39:44","guid":{"rendered":"https:\/\/acua.qcri.org\/blog\/?p=645"},"modified":"2023-04-22T11:39:44","modified_gmt":"2023-04-22T08:39:44","slug":"finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels","status":"publish","type":"post","link":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/","title":{"rendered":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels"},"content":{"rendered":"<figure id=\"attachment_646\" aria-describedby=\"caption-attachment-646\" style=\"width: 625px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\" wp-image-646\" src=\"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-1024x518.png\" alt=\"Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels\" width=\"625\" height=\"316\" srcset=\"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-1024x518.png 1024w, https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-300x152.png 300w, https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-768x389.png 768w, https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023.png 1170w\" sizes=\"(max-width: 625px) 100vw, 625px\" \/><figcaption id=\"caption-attachment-646\" class=\"wp-caption-text\"><a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-023-10395-5#citeas\" target=\"_blank\" rel=\"noopener\">Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels<\/a><\/figcaption><\/figure>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">Although the effect of hyperparameters on algorithmic outputs is well-known in machine learning, the effects of hyperparameters on informati<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">on systems that produce user or customer segments are relatively unexplored.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">This research employs the concept of persona and the effect of varying the number of user segments on the personification of user engagement data in a real analytics information system.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">We increment the number of personas from 5 to 15 for a total of 330 personas and 33 persona generations. We then examine the effect of changing the hyperparameter on the gender, age, nationality, and combined gender-age-nationality representation of the user population.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">The results show that despite using the same data and algorithm, varying the number of personas strongly biases the information system\u2019s personification of the user population. The hyperparameter selection for the 990 total personas results in an average deviation of 54.5% for gender, 42.9% for age, 28.9% for nationality, and 40.5% for gender-age-nationality.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">A repeated analysis of two other organizations shows similar results for all attributes. The deviation occurred for all organizations on all platforms for all attributes, as high as 90.9% in some cases.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">The results imply that decision-makers using analytics information systems should be aware of the effect of hyperparameters on the set of user or customer segments they are exposed to.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">Organizations looking to use persona analytics systems effectively must be wary that altering the number of personas could substantially change the results, leading to drastically different interpretations of the actual user base.<\/p>\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">\n<p style=\"box-sizing: inherit; margin: 0px; padding: 0px; border: var(--artdeco-reset-base-border-zero); vertical-align: var(--artdeco-reset-base-vertical-align-baseline); background-color: #ffffff; --artdeco-reset-typography_getfontsize: 1.6rem; --artdeco-reset-typography_getlineheight: 1.5; line-height: var(--artdeco-reset-typography_getLineHeight); color: rgba(0, 0, 0, 0.9); cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; font-family: -apple-system, system-ui, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Fira Sans', Ubuntu, Oxygen, 'Oxygen Sans', Cantarell, 'Droid Sans', 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Lucida Grande', Helvetica, Arial, sans-serif; white-space: pre-wrap;\">The article is gold open access.<\/p>\n<p>Jansen, B. J., Jung, S.G., and Salminen, J. (2023)\u00a0<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-023-10395-5#citeas\" target=\"_blank\" rel=\"noopener\">Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels<\/a>,\u00a0<u>Information Systems Frontiers<\/u>. https:\/\/doi.org\/10.1007\/s10796-023-10395-5<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Although the effect of hyperparameters on algorithmic outputs is well-known in machine learning, the effects of hyperparameters on informati on systems that produce user or customer segments are relatively unexplored. This research employs the concept of persona and the effect of varying the number of user segments on the personification of user engagement data in&hellip; <a class=\"more-link\" href=\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\">Continue reading <span class=\"screen-reader-text\">\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v19.13 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua\" \/>\n<meta property=\"og:description\" content=\"Although the effect of hyperparameters on algorithmic outputs is well-known in machine learning, the effects of hyperparameters on informati on systems that produce user or customer segments are relatively unexplored. This research employs the concept of persona and the effect of varying the number of user segments on the personification of user engagement data in&hellip; Continue reading \u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels\" \/>\n<meta property=\"og:url\" content=\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\" \/>\n<meta property=\"og:site_name\" content=\"Team Acua\" \/>\n<meta property=\"article:published_time\" content=\"2023-04-22T08:39:44+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-1024x518.png\" \/>\n<meta name=\"author\" content=\"Jim Jansen\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Jim Jansen\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\"},\"author\":{\"name\":\"Jim Jansen\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/e3bb7a0b58349e548e8940716694c215\"},\"headline\":\"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels\",\"datePublished\":\"2023-04-22T08:39:44+00:00\",\"dateModified\":\"2023-04-22T08:39:44+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\"},\"wordCount\":327,\"publisher\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/#organization\"},\"articleSection\":[\"Customer segmentation\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\",\"url\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\",\"name\":\"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua\",\"isPartOf\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/#website\"},\"datePublished\":\"2023-04-22T08:39:44+00:00\",\"dateModified\":\"2023-04-22T08:39:44+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/acua.qcri.org\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#website\",\"url\":\"https:\/\/acua.qcri.org\/blog\/\",\"name\":\"Team Acua\",\"description\":\"Audience, Customer, and User Analytics\",\"publisher\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/acua.qcri.org\/blog\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#organization\",\"name\":\"Team Acua\",\"url\":\"https:\/\/acua.qcri.org\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2022\/10\/cropped-cropped-logo.png\",\"contentUrl\":\"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2022\/10\/cropped-cropped-logo.png\",\"width\":1466,\"height\":770,\"caption\":\"Team Acua\"},\"image\":{\"@id\":\"https:\/\/acua.qcri.org\/blog\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/e3bb7a0b58349e548e8940716694c215\",\"name\":\"Jim Jansen\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/a4f97370631247bb1aed9a897d658981?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/a4f97370631247bb1aed9a897d658981?s=96&d=mm&r=g\",\"caption\":\"Jim Jansen\"},\"sameAs\":[\"https:\/\/quecst.qcri.org\/blog\"],\"url\":\"https:\/\/acua.qcri.org\/blog\/author\/jjansenacm-org\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/","og_locale":"en_US","og_type":"article","og_title":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua","og_description":"Although the effect of hyperparameters on algorithmic outputs is well-known in machine learning, the effects of hyperparameters on informati on systems that produce user or customer segments are relatively unexplored. This research employs the concept of persona and the effect of varying the number of user segments on the personification of user engagement data in&hellip; Continue reading \u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels","og_url":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/","og_site_name":"Team Acua","article_published_time":"2023-04-22T08:39:44+00:00","og_image":[{"url":"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2023\/04\/depersonification_personification_2023-1024x518.png"}],"author":"Jim Jansen","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Jim Jansen","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#article","isPartOf":{"@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/"},"author":{"name":"Jim Jansen","@id":"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/e3bb7a0b58349e548e8940716694c215"},"headline":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels","datePublished":"2023-04-22T08:39:44+00:00","dateModified":"2023-04-22T08:39:44+00:00","mainEntityOfPage":{"@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/"},"wordCount":327,"publisher":{"@id":"https:\/\/acua.qcri.org\/blog\/#organization"},"articleSection":["Customer segmentation"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/","url":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/","name":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels - Team Acua","isPartOf":{"@id":"https:\/\/acua.qcri.org\/blog\/#website"},"datePublished":"2023-04-22T08:39:44+00:00","dateModified":"2023-04-22T08:39:44+00:00","breadcrumb":{"@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/acua.qcri.org\/blog\/finetuning-analytics-information-systems-for-a-better-understanding-of-users-evidence-of-personification-bias-on-multiple-digital-channels\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/acua.qcri.org\/blog\/"},{"@type":"ListItem","position":2,"name":"\u00a0Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels"}]},{"@type":"WebSite","@id":"https:\/\/acua.qcri.org\/blog\/#website","url":"https:\/\/acua.qcri.org\/blog\/","name":"Team Acua","description":"Audience, Customer, and User Analytics","publisher":{"@id":"https:\/\/acua.qcri.org\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/acua.qcri.org\/blog\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/acua.qcri.org\/blog\/#organization","name":"Team Acua","url":"https:\/\/acua.qcri.org\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/acua.qcri.org\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2022\/10\/cropped-cropped-logo.png","contentUrl":"https:\/\/acua.qcri.org\/blog\/wp-content\/uploads\/2022\/10\/cropped-cropped-logo.png","width":1466,"height":770,"caption":"Team Acua"},"image":{"@id":"https:\/\/acua.qcri.org\/blog\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/e3bb7a0b58349e548e8940716694c215","name":"Jim Jansen","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/acua.qcri.org\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/a4f97370631247bb1aed9a897d658981?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a4f97370631247bb1aed9a897d658981?s=96&d=mm&r=g","caption":"Jim Jansen"},"sameAs":["https:\/\/quecst.qcri.org\/blog"],"url":"https:\/\/acua.qcri.org\/blog\/author\/jjansenacm-org\/"}]}},"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/posts\/645"}],"collection":[{"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/comments?post=645"}],"version-history":[{"count":1,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/posts\/645\/revisions"}],"predecessor-version":[{"id":647,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/posts\/645\/revisions\/647"}],"wp:attachment":[{"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/media?parent=645"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/categories?post=645"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/acua.qcri.org\/blog\/wp-json\/wp\/v2\/tags?post=645"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}