ABOUT THIS VIDEO
这一期,聊些什么? 约90秒连续实操节选:Claire Vo展示如何接入YouTube评论,将留言分成正面、负面与中性,标记包含未来节目建议的评论,并生成反馈与选题看板。片中约4500条评论、58条建议来自作者当时的演示数据,分类结果仍需判断。原视频由How I AI于2026年9月28日发布,本片取自约18:46至20:36。需要YouTube接口与模型配置,并非视频号的现成功能。画面使用YouTube原视频,本站仅保存独立音轨与文稿;中文音轨不混入原来的英文人声。
这段演示的流程 先明确想知道什么 作者想了解评论情绪,也想找到观众对下一期节目的建议。先有问题,再让模型分类。
拉取评论,再做两类标记 原片通过YouTube v3接口拉取评论;先判断正面、负面或中性,再标记是否包含选题建议。实际使用需要接口与模型配置。
看板展示结果,继续人工判断 原片展示情绪分类和观众选题建议板。约4500条评论与58条建议是作者当时的数据,模型标记不能替代对评论含义的判断。
显示语言 中英对照 中文 English 跟随播放
点击段落跳转到对应时间
0:00 第一个演示,是How I AI节目的观众反馈看板。 So the first one I want to do is How I AI audience signals. 0:06 各位观众会在How I AI节目下面留下评论。我每天都会一条条读,有时间就回复。不过,我以前一直没有对这些留言做过系统分析。 So you wonderful people give us comments on the How I AI podcast, and I go through them. I read them every day and I reply to them when I can, but I have never done analysis on them. 0:20 大约四千五百条评论,我想知道大家是满意还是不满。 And there are about 4,500 comments, and I just wanted to know: are they good? Are they bad? Are they happy? Are they sad? 0:27 我还想提取大家对未来节目的建议,比如这期Jev。于是,我接入YouTube的v3接口,在Google控制台启用就行。 And I also wanted to know if you all had any episode ideas for me, where I could extract them and come up with episodes that I could do, like this Jev one. And so I hooked up the YouTube V3 API. You just have to enable it in Google Console. 0:43 然后我说:拉取所有评论,分成正面、负面和中性。 And then I said, pull all the comments and categorize them into positive, negative, or neutral. 0:50 这可以用Choice,也就是选择分类,也许也能用Score评分。接着让Jev判断评论里有没有未来节目的想法,再分析所有数据,给我生成看板。 So that would be a choice, right? Or a score, probably. And then I said, also use Jev to identify whether or not includes an idea for a future episode, and then analyze all the data and give me a dashboard to look at the data. 1:04 从这里可以看到,大约一半的评论是正面的,有五十八条提出了未来节目的想法。还有一类是制作质量好评,在夸我们的制作团队,比如节目画面很好看。 And so you can see here, about half are positive. There are 58 comments in here with episode ideas, and then there is quality praise, which is praise for our production team, like how nice the podcast looks. 1:19 它生成的看板会标出正面、中性、负面或混合情绪,还做了一个观众选题建议板。 And so then it made me this dashboard which is telling me, is it positive, neutral, negative, or mixed? And then it gave me an audience request board.
没有匹配的文稿