php如何減緩gc

With more people now than ever relying on social media to stay updated on current events, there is an ethical responsibility for hosting companies to defend against false information. Disinformation, which is a type of misinformation that is intended to manipulate and mislead, can create unrest and panic. Other types of misinformation such as rumors and hoaxes, if left unchecked, also has the potential to bring mental and physical harm to unwary readers. The key to stopping the spread of misinformation is taking swift action against them since they have the tendency to travel very quickly. In fact, studies show that falsehood spreads exponentially faster than the truth (source). Social media companies have put in place protocols to limit the virality of inaccurate content, but they only take effect once the content has been reviewed by third-party fact-checking partners. Therefore, the focus is on rapid assessment of veracity. We’ve seen remarkable ingenuity from technology companies in this capacity. Namely, the use of Machine Learning algorithms to complement fact-checking programs for identifying inaccurate content. However, this is yet to be a complete solution. In this article, we’ll study the process and explore how it might evolve.

如今，比以往任何時(shí)候都更多的人依賴社交媒體來了解最新新聞，因此托管公司有道德責(zé)任承擔(dān)防范虛假信息的責(zé)任。 虛假信息是一種旨在操縱和誤導(dǎo)的虛假信息，會引起騷動和恐慌。 如果不加以制止，其他類型的錯(cuò)誤信息，例如謠言和惡作劇，也有可能給粗心的讀者帶來精神和身體上的傷害。 阻止錯(cuò)誤信息傳播的關(guān)鍵是對它們采取Swift的行動，因?yàn)樗鼈儍A向于快速傳播。 實(shí)際上，研究表明，虛假的傳播速度比真相的傳播速度快( 來源 )。 社交媒體公司已經(jīng)制定了協(xié)議來限制不準(zhǔn)確內(nèi)容的病毒性，但是只有在第三方事實(shí)檢查合作伙伴對內(nèi)容進(jìn)行審核后，它們才會生效。 因此，重點(diǎn)是對準(zhǔn)確性進(jìn)行快速評估。 我們已經(jīng)看到技術(shù)公司在此方面具有非凡的創(chuàng)造力。 即，使用機(jī)器學(xué)習(xí)算法來補(bǔ)充事實(shí)檢查程序，以識別不正確的內(nèi)容。 但是，這尚未成為一個(gè)完整的解決方案。 在本文中，我們將研究該過程并探討其可能如何發(fā)展。

如何識別錯(cuò)誤信息 (How Misinformation is Identified)

Fact-Checking Program workflow事實(shí)檢查計(jì)劃工作流程

The process of evaluating the content’s accuracy begins with an internal screening of potential falsehood. This involves the utilization of Automation and Machine Learning models to pick up various signals. If the content is determined to potentially be misinformation, it’s routed to fact-checking partners for further review. After manual research and/or consultation with the primary source, a content rating is assigned. The resulting rating notifies the social media company if action needs to be taken. Further, the rating also helps train the Machine Learning models to become better at catching misinformation in the future. Below is how Machine Learning contributes to the process:

評估內(nèi)容準(zhǔn)確性的過程始于對潛在虛假性的內(nèi)部篩選。 這涉及利用自動化和機(jī)器學(xué)習(xí)模型來拾取各種信號。 如果確定內(nèi)容可能是錯(cuò)誤信息，則將其發(fā)送給事實(shí)檢查合作伙伴以進(jìn)行進(jìn)一步檢查。 在對主要來源進(jìn)行人工研究和/或咨詢后，會分配內(nèi)容分級。 如果需要采取行動，則由此產(chǎn)生的評級將通知社交媒體公司。 此外，該等級還有助于訓(xùn)練機(jī)器學(xué)習(xí)模型，使其在將來更好地捕捉錯(cuò)誤信息。 以下是機(jī)器學(xué)習(xí)對流程的貢獻(xiàn)：

• The prediction models significantly reduce the number of reviews third-party fact-checking partners need to perform
  預(yù)測模型大大減少了第三方事實(shí)檢查合作伙伴需要執(zhí)行的審閱次數(shù)
• Finding duplicate or near-duplicate content frees up capacity for fact-checking partners to review new instances of misinformation
  查找重復(fù)或幾乎重復(fù)的內(nèi)容可釋放事實(shí)檢查合作伙伴查看新的錯(cuò)誤信息實(shí)例的能力

It’s quite a robust process, but not one without challenges. Below are the main challenges for this process:

這是一個(gè)強(qiáng)大的過程，但并非沒有挑戰(zhàn)。 以下是此過程的主要挑戰(zhàn)：

• The large and growing number of active users makes the platform a target for coordinated propaganda attacks, bringing urgency and heavy workload for the fact-checking program
  大量活躍用戶使該平臺成為協(xié)調(diào)宣傳攻擊的目標(biāo)，為事實(shí)檢查程序帶來了緊迫性和繁重的工作量
• The scarcity of verified deceptive content to be used as the corpora for predictive classification model training is a roadblock for Machine Learning methods. This is further exacerbated by the desire to have more narrow categories of “truthiness” since they require different treatments, thus diluting the available data
  缺乏可用于預(yù)測分類模型訓(xùn)練的經(jīng)過驗(yàn)證的欺騙性內(nèi)容是機(jī)器學(xué)習(xí)方法的障礙。 由于對“真實(shí)性”的分類更窄，因此它們的需求進(jìn)一步加劇，因?yàn)樗鼈冃枰煌奶幚矸绞?#xff0c;從而稀釋了可用數(shù)據(jù)
• “Bad actors” who hide misleading context behind genuine content are hard to detect. For example, a Meme can use text layered on top of a photo or video to form deceitful content
  在真實(shí)內(nèi)容后隱藏誤導(dǎo)性上下文的“壞演員”很難被發(fā)現(xiàn)。 例如，一個(gè)Meme可以使用在照片或視頻上分層的文字來構(gòu)成欺騙性內(nèi)容
• Satirical may be misunderstood by people and are even more difficult for computers
  諷刺語可能會被人們誤解，并且對于計(jì)算機(jī)而言甚至更加困難

Monthly Active Users continue to grow as social media become the dominant medium for people to get news隨著社交媒體成為人們獲取新聞的主要媒介，每月活躍用戶持續(xù)增長

仔細(xì)檢查篩選過程 (A Closer Look at the Screening Process)

Automation and Machine Learning look for signals to screen content自動化和機(jī)器學(xué)習(xí)尋找屏幕內(nèi)容的信號

開發(fā)中 (In Development)

Technology companies are working to improve this process by significantly expanding their databases that will help them build Artificial Intelligence to combat sophisticated attacks such as “deep fakes” and “weaponized memes”. The effectiveness of the algorithms and models largely depend on the having a diverse data set to train on. Fortunately, with the wide collaboration across the technology community in terms of data sharing, the models are becoming better at understanding content. Nevertheless, this is work in progress.

科技公司正在努力通過顯著擴(kuò)展其數(shù)據(jù)庫來改善此過程，這將幫助它們構(gòu)建人工智能來對抗復(fù)雜的攻擊，例如“深造假”和“武器化模因”。 算法和模型的有效性在很大程度上取決于要訓(xùn)練的多樣化數(shù)據(jù)集。 幸運(yùn)的是，隨著整個(gè)技術(shù)社區(qū)在數(shù)據(jù)共享方面的廣泛合作，這些模型在理解內(nèi)容方面變得越來越好。 盡管如此，這項(xiàng)工作仍在進(jìn)行中。

推薦建議 (Recommendations)

There are considerations that should be explored to make immediate improvements. One recommendation that I’m exploring is the prioritization and specialization of contents for third-party fact-checkers. We can perform A/B testing to compare the turn-over and overall virality to measure the impact of these measures.

應(yīng)該探索一些考慮因素以立即進(jìn)行改進(jìn)。 我正在探索的一項(xiàng)建議是對第三方事實(shí)檢查者的內(nèi)容進(jìn)行優(yōu)先級劃分和專業(yè)化處理。 我們可以進(jìn)行A / B測試，以比較周轉(zhuǎn)率和整體病毒性來衡量這些措施的影響。

• Prioritization of dangerous content that have a propensity to spread before they become viral
  優(yōu)先確定容易傳播的易于傳播的危險(xiǎn)內(nèi)容
• Specialization of content directs content to third-party fact-checkers within their area of expertise to cut the amount of time require to review
  內(nèi)容的專業(yè)化將內(nèi)容定向到其專業(yè)領(lǐng)域內(nèi)的第三方事實(shí)檢查人員，以減少審核所需的時(shí)間

摘要 (Summary)

Infodemic is a disease that has plague us long before the recent health crisis. Without proper management, it can do tremendous harm to our society. Thankfully, there are technological tools to help us mitigate those risks. We reviewed the fact-checking progress and specifically how Machine Learning is being applied in this use case.

信息病是在最近的健康危機(jī)之前很久困擾我們的疾病。 如果沒有適當(dāng)?shù)墓芾?#xff0c;它將對我們的社會造成巨大傷害。 值得慶幸的是，有技術(shù)工具可以幫助我們減輕這些風(fēng)險(xiǎn)。 我們回顧了事實(shí)檢查的進(jìn)展，特別是在此用例中如何應(yīng)用機(jī)器學(xué)習(xí)。

翻譯自: https://towardsdatascience.com/managing-infodemics-slowing-the-spread-of-misinformation-b8b74e3e2618

php如何減緩gc

總結(jié)

以上是生活随笔為你收集整理的php如何减缓gc_管理信息传播-使用数据科学减缓错误信息的传播的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。