2021 年,我们如何抵御 Google 搜索中的网络垃圾
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
2022 年 4 月 21 日(星期四)
2021 年,世界各地的用户搜索了如何减少全球疫情的影响以及如何以更强大的姿态回归。为了帮助用户找到各种大大小小问题的实用信息,我们力求将网络垃圾和恶意内容排除在 Google 搜索之外。
SpamBrain:我们最有效的抵御网络垃圾的解决方案
与近 20 年前首次推出该解决方案时相比,2021 年我们发现的垃圾网站数量要多出 200 倍,这在一定程度上要归功于我们基于 AI 的网络垃圾防范系统 SpamBrain。
SpamBrain 于 2018 年推出,我们一直在不断提高其性能。2021 年,SpamBrain 发现的垃圾网站比 2020 年多了近 6 倍。这使被黑网络垃圾(2020 年常常发现的网站垃圾类型)大幅减少 70%,托管平台上的乱码网络垃圾大幅减少 75%。SpamBrain 的另一个显著功能是,它旨在成为一个强大且不断发展的平台,以解决各类滥用行为。
由于每天都会出现大量的复杂网络垃圾,SpamBrain 可识别数十亿网页中存在的干扰性和恶意行为的能力可实现超过 99% 用户搜索不含网络垃圾。
保护搜索质量和用户安全
2021 年,我们在抵御传统网络垃圾之外,还取得了多方面的重大进展:主要是打击链接垃圾内容、诈骗和网络骚扰。
链接仍然有助于我们以有意义的方式发现结果并对其进行排名。2021 年,我们在保护这一核心信号方面取得了很大进展。我们发布了垃圾链接更新,以广泛识别非自然链接并防止它们影响搜索质量。
诈骗是在线用户安全面临的一个巨大威胁。我们在 2020 年进一步扩大了研究范围,推出了多项算法更新,从而使诈骗结果减少了 40%。除了我们在过去几年一直力求解决的客户服务查询诈骗之外,我们还扩大了覆盖范围,保护用户免受更多诈骗手段的侵扰。
为了保护用户安全,我们已扩展 SpamBrain 的功能,以解决网络骚扰;对于针对姓名的查询,我们会采取有偿移除做法来降低网站的显眼程度。
降低排名操纵的影响
除网络垃圾之外,我们还会努力减少低质量内容和打击排名操纵,具体做法是打击试图以擦边方式不违反我们质量指南但本质上仍然具有操纵性并会影响用户体验的行为。
例如,该计划的一个方面是提高商品评价查询的排名;在这种情况下,内容通常由重写的商品说明组成,而非真实的亲身体验评价。我们在 2021 年对我们评估商品评价的方式进行了两项重大更新,大幅降低了低质量评价,同时优先展示提供优质内容和专业知识的评价。
我们希望确保用户能够通过 Google 搜索找到最有用的内容。如果您在搜索结果中发现操纵行为,可以直接在搜索结果页上向我们发送反馈。
发布者:Cody Kwok,首席工程师
如未另行说明,那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可,并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情,请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
[null,null,[],[[["\u003cp\u003eGoogle's AI-based system, SpamBrain, significantly reduced spam in search results in 2021, identifying nearly six times more spam sites than in 2020.\u003c/p\u003e\n"],["\u003cp\u003eGoogle launched updates to combat link spam, scams, and online harassment, resulting in a 40% reduction in scammy results and improved protection for users.\u003c/p\u003e\n"],["\u003cp\u003eEfforts were made to improve the ranking of product review queries by reducing low-quality reviews and promoting genuine, hands-on reviews with expertise.\u003c/p\u003e\n"],["\u003cp\u003eGoogle is actively working to reduce manipulative behaviors that degrade user experience, even if they don't directly violate quality guidelines.\u003c/p\u003e\n"],["\u003cp\u003eUsers are encouraged to provide feedback on manipulative behaviors encountered in search results to help Google further enhance search quality.\u003c/p\u003e\n"]]],["In 2021, Google's SpamBrain, an AI-based system, significantly improved spam detection, identifying six times more spam sites than in 2020, leading to a 70% decrease in hacked spam and a 75% reduction in gibberish spam. Google also launched a link spam update, reduced scammy results by 40%, and expanded SpamBrain to combat online harassment. They refined product review ranking to promote genuine expertise, and reduced low quality content. They encourage users to send feedback on manipulative search results.\n"],null,["# How we fought Search spam on Google in 2021\n\nThursday, April 21, 2022\n\n\nIn 2021, the world searched for [how to heal and how to come back stronger](https://blog.google/products/search/year-in-search-2021/). To help people find helpful information on questions big and small, we worked to keep spam and malicious content away from Search.\n\nSpamBrain: our most effective solution against spam\n---------------------------------------------------\n\n\nWe caught 200 times more spam sites in 2021 compared to when we first started nearly two decades ago, thanks, in part, to our AI-based spam-prevention system called SpamBrain.\n\n\nSpamBrain was launched [in 2018](/search/blog/2020/06/how-we-fought-search-spam-on-google#spam-trends) and we've been continuously improving its performance. In 2021, SpamBrain identified nearly six times more spam sites than in 2020. This resulted in a major reduction in hacked spam (70%), which was a spam type commonly observed in 2020, and gibberish spam on hosting platforms (75%). Another notable feature of SpamBrain is that it was built to be a robust and evolving platform to address all types of abuse.\n\n\nWith an increasing volume of sophisticated spam being produced every day, SpamBrain's ability to identify disruptive and malicious behaviors among billions of web pages has allowed us to keep more than 99% of searches spam-free.\n\nProtecting search quality and user safety\n-----------------------------------------\n\n\nWe made significant progress in several areas beyond traditional web spam in 2021: most notably in fighting link spam, scams, and online harassment.\n\n\nLinks still help us discover and rank results in meaningful ways, and we made a lot of progress in 2021 to protect this core signal. We launched a [link spam update](/search/blog/2021/07/link-tagging-and-link-spam-update) to broadly identify unnatural links and prevent them from affecting search quality.\n\n\nScams are a [big threat to online user safety](https://www.ftc.gov/news-events/news/press-releases/2022/02/new-data-shows-ftc-received-28-million-fraud-reports-consumers-2021-0). Expanding on [our work in 2020](/search/blog/2021/04/how-we-fought-search-spam-2020#protecting-you-beyond-spam), we launched several algorithm updates that resulted in a 40% reduction of scammy results. The improvement in coverage allowed us to protect people against many more scam types beyond the customer support queries that we've been fighting for the past few years.\n\n\nTo protect user safety, we extended SpamBrain to [address online harassment](https://blog.google/products/search/improving-search-better-protect-people-harassment/) and, for name queries, reduce the prominence of sites with exploitative removal practices.\n\nReducing the effects of ranking manipulation\n--------------------------------------------\n\n\nBesides spam, we also work hard to reduce low quality content and ranking manipulations by fighting behaviors that attempt to narrowly avoid violating [our quality guidelines](/search/docs/advanced/guidelines/overview), but are still manipulative in nature and degrade the user experience.\n\n\nFor example, one aspect of this initiative was to improve the ranking of product review queries, where content often consisted of rewritten product descriptions, and not genuine, hands-on reviews. We made two substantial updates to [how we evaluate product reviews](/search/blog/2021/12/product-reviews-update-and-your-site) in 2021 that resulted in significant reduction in low quality reviews, while promoting ones with better content and expertise.\n\n\nWe want to make sure there's nothing getting in the way of people finding the most useful content through Search. If you see manipulative behaviors in search results, you can [send us feedback](https://support.google.com/websearch/answer/3338405) right on the search results page.\n\nPosted by Cody Kwok, Principal Engineer"]]