PersaLog

Abstract

Content personalization-automatically modifying text and multimedia features within articles based on the reader's individual features-is evolving as a new form of journalism. Informed by constraints articulated through a survey of journalists, we have implemented PersaLog, a novel system for creating personalized content (e.g., text and interactive visualizations). Because crafting, and validating, personalized content can be challenging to scale across articles (unlike feed personalization), we offer a simple Domain Specific Language (DSL), and editing environment, to support this task. Persa-Log is particularly designed to support the personalization of existing text and visualizations. Our work provides guidelines for personalization as well as a system that allows for both subtle and dramatic personalization-driven content changes. We validate PersaLog using case and lab studies.

Know Your Audience: The benefits and pitfalls of generating plain language summaries beyond the "general" audience

“…There is a rich literature on adaptive interfaces and personalization in many domains, including website design [86], advertisement [46,101], study recruitment [8], journalism [2], and education [35,38,77]. Usually personalization focuses on adjusting visual elements, but work has also shown the benefit of adjusting language to different audiences.…”

“…Prior work has found that such tailoring of patient pamphlets can improve health outcomes, including smoking behavior and future health complications [66,96,100]. In journalism, Adar et al [2] introduced PersaLog, a system for authoring personalized news articles. Articles authored using PersaLog presented alternative content (e.g., heat estimates for different areas) depending on user traits (e.g., a user's location).…”

“…Previous adaptive language-based interfaces have either relied on experts to author multiple versions of content [2], used rules and templates to automatically adjust content [34,78], or focused on specialized populations (e.g., researchers [71]). Manually writing versions of text for each possible reader is infeasible, and rulebased approaches are brittle and only applicable to narrow content adaptation.…”

Artificial Intelligence and Automated Journalism: Contemporary Challenges and New Opportunities

“…In this respect, Smith and Linden (2017) showed that filtering algorithms capable collect, sort and prioritize data about the users' behavior [60]. In 2017, some scholars conducted a study entitled: PersaLog: Personalization of News Article Contentthey introduced the PersaLog system for journalism professionals which able to content personalization, as well as enhance learning and behavioral changes in readers and increase engagement [61]. In sum, news sites today can be offering everything most users need by using "cookies", such as personalized content by register different information from real uses of users while they act on the given website [62].…”

Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts

“…capabilities, LLMs have the potential to change creative language arts (CLA) 1 . New LLM-based tools can provide authors with AIgenerated suggestions based on the author's own writing or instructions [18,58].…”