发表机构
Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对个性化新闻推荐，提出偏好-曝光-消费（PEC）审计框架，分离三层次数据，实证发现其不一致性，强调审计需明确测量维度。
AI 中文摘要
个性化新闻平台常常被评估为仿佛陈述偏好、记录的推荐曝光和点击消费构成一个单一连贯的流程。将这些层次合并可能会扭曲审计结论：一个平台可能显得比观察到的点击消费所支持的更一致或更多样化，这可能会误导多样性治理或算法干预。我们引入了一个可复用的偏好-曝光-消费（PEC）审计框架，在明确的可见性边界下，分离陈述偏好、观察到的加权画像状态、记录的推荐曝光、应用界面路径和点击消费。利用一个已部署的移动新闻应用六个月的日志，我们审计了1,583个用户画像、95,143条记录的推荐项和17,512个点击事件。每种轨迹类型贡献了不同的信息；没有任何一种能直接替代另一种。偏好-消费一致性超过了基于机会的零基线，但仅捕捉了用户最常消费类别集合的一部分。记录的推荐列表包含被点击文章的频率高于日期匹配的候选池基线所预测的（11.29%对比9.13%；前5名提升1.47倍），但许多点击通过其他应用界面到达。在计数匹配下，原始曝光-消费多样性差距缩小，但在符合审计资格的队列中，集中度不匹配仍然存在（HHI差距0.082）。总体而言，结果表明，审计结论取决于平台是衡量陈述偏好、记录的曝光还是点击消费。
英文摘要
Personalized news platforms are often evaluated as if stated preferences, logged recommendation exposure, and click consumption form a single coherent pipeline. Collapsing these layers can distort audit conclusions: a platform may appear more aligned or diverse than observed click consumption supports, which can misdirect diversity governance or algorithmic intervention. We introduce a reusable Preference-Exposure-Consumption (PEC) audit framework that separates stated preference, observed weighted profile state, logged recommendation exposure, app-surface pathways, and click consumption under explicit observability boundaries. Using six months of logs from a deployed mobile news application, we audit 1,583 user profiles, 95,143 logged recommendation items, and 17,512 click events. Each trace type contributes distinct information; none directly substitutes for another. Preference-consumption alignment exceeds chance-based null baselines but captures only part of users' top-consumed category set. Logged recommendation lists contain clicked articles more often than a date-matched candidate-pool baseline predicts (11.29% vs 9.13%; top-5 lift 1.47x), but many clicks arrive through other app surfaces. Raw exposure-consumption diversity gaps shrink under count matching, yet concentration mismatch persists in the audit-eligible cohort (HHI gap 0.082). Together, the results show that audit conclusions change depending on whether platforms measure stated preference, logged exposure, or click consumption.
Comments16 pages, 5 figures, 14 tables. Submitted to ICWSM 2027
