Filter bubbles have been studied extensively within the context of online
content platforms due to their potential to cause undesirable outcomes such as
user dissatisfaction or polarization. With the rise of short-video platforms,
the filter bubble has been given extra attention because these platforms rely
on an unprecedented use of the recommender system to provide relevant content.
In our work, we investigate the deep filter bubble, which refers to the user
being exposed to narrow content within their broad interests. We accomplish
this using one-year interaction data from a top short-video platform in China,
which includes hierarchical data with three levels of categories for each
video. We formalize our definition of a "deep" filter bubble within this
context, and then explore various correlations within the data: first
understanding the evolution of the deep filter bubble over time, and later
revealing some of the factors that give rise to this phenomenon, such as
specific categories, user demographics, and feedback type. We observe that
while the overall proportion of users in a filter bubble remains largely
constant over time, the depth composition of their filter bubble changes. In
addition, we find that some demographic groups that have a higher likelihood of
seeing narrower content and implicit feedback signals can lead to less bubble
formation. Finally, we propose some ways in which recommender systems can be
designed to reduce the risk of a user getting caught in a bubble.

在这项研究中，我们通过在中国一家顶级短视频平台的一年交互数据，对 “深度” 筛选气泡进行了调查，该平台包括每个视频的三级类别的层次数据，我们对这种情况下的 “深度” 筛选气泡进行了形式化定义，然后在数据中探索了各种相关性，首先了解了深度筛选气泡随时间的演变，然后揭示了导致该现象的一些因素，如特定类别、用户人口统计数据和反馈类型。我们观察到，尽管筛选气泡中用户的整体比例随时间基本保持不变，但其筛选气泡的深度构成会发生变化。此外，我们发现一些具有更大可能性看到较狭窄内容和隐性反馈信号的人口群体会导致较少的筛选气泡形成。最后，我们提出了一些减少用户陷入气泡风险的推荐系统设计方法。

揭示深度过滤泡：短视频推荐中的狭窄曝光

Uncovering the Deep Filter Bubble: Narrow Exposure in Short-Video  Recommendation

Echoing the history of search engines and social media content rankings, the
advent of large language models (LLMs) has led to a push for increased
personalization of model outputs to individual users. In the past, personalized
recommendations and ranking systems have been linked to the development of
filter bubbles (serving content that may confirm a user's existing biases) and
affective polarization (strong negative sentiment towards those with differing
views). In this work, we explore how prompting a leading large language model,
ChatGPT-3.5, with a user's political affiliation prior to asking factual
questions about public figures and organizations leads to differing results. We
observe that left-leaning users tend to receive more positive statements about
left-leaning political figures and media outlets, while right-leaning users see
more positive statements about right-leaning entities. This pattern holds
across presidential candidates, members of the U.S. Senate, and media
organizations with ratings from AllSides. When qualitatively evaluating some of
these outputs, there is evidence that particular facts are included or excluded
based on the user's political affiliation. These results illustrate that
personalizing LLMs based on user demographics carry the same risks of affective
polarization and filter bubbles that have been seen in other personalized
internet technologies. This ``failure mode" should be monitored closely as
there are more attempts to monetize and personalize these models.

对个人化的大型语言模型输出进行用户政治倾向性的引导，发现左倾用户更容易接收到对左派政界人物和媒体机构的正面评价，而右倾用户则更容易接收到对右派实体的正面评价。这种个人化模式会带来情感极化和过滤泡沫的风险。

用户个性化大型语言模型输出中的筛选泡和情感极化

Filter bubbles and affective polarization in user-personalized large  language model outputs

TikTok is a video-sharing social networking service, whose popularity is
increasing rapidly. It was the world's second-most downloaded app in 2019.
Although the platform is known for having users posting videos of themselves
dancing, lip-syncing, or showcasing other talents, user-videos expressing
political views have seen a recent spurt. This study aims to perform a primary
evaluation of political communication on TikTok. We collect a set of US
partisan Republican and Democratic videos to investigate how users communicated
with each other about political issues. With the help of computer vision,
natural language processing, and statistical tools, we illustrate that
political communication on TikTok is much more interactive in comparison to
other social media platforms, with users combining multiple information
channels to spread their messages. We show that political communication takes
place in the form of communication trees since users generate branches of
responses to existing content. In terms of user demographics, we find that
users belonging to both the US parties are young and behave similarly on the
platform. However, Republican users generated more political content and their
videos received more responses; on the other hand, Democratic users engaged
significantly more in cross-partisan discussions.

通过计算机视觉和自然语言处理等手段，探究用户在 TikTok 等社交媒体平台上的政治传播，并发现与其它平台相比，政治传播更具有互动性，用户更倾向于通过生成响应分支的方式展开政治交流。