# Why Did That Weibo Post Take Off? Pull Out Its Angle and the Mood in Its Comments, and Turn Them Into Your Next Topic

> Once a single Weibo post is in your Beav knowledge base, click Decompose on it to get a topic, a structure template and the original text, with the topic also added to the topic center. Leave the comments to a chat: ask the AI to read the public comments on request, sum up the feelings, questions and disagreements in them, and note the angles worth covering in your topic pool. What uses quota, and how it compares with handwritten notes, highlighting in a document and asking a general AI for a summary.

- Source: https://beav.pro/en/blog/features/weibo-breakdown-structure
- Author: JambaHailar (https://x.com/JambaHailar), Beav
- Published: 2026-11-19
- Last updated: 2026-11-19

> **Key takeaways**
>
> * Once a Weibo post is in your knowledge base, open it and click **Decompose**. You get a topic, a structure template and the original text, and the topic is also added to the topic center. A text-only post has no shots, clips or music.
> * The mood in the comments isn't part of the decomposition. Send the post's exact link in a chat and ask the AI to read the public comments and sum up what people are angry about, asking about and arguing over. That's an answer in the chat, not decomposition output.
> * Decomposition only starts when you click it and uses model quota. Copy the angles you like into the **Topic pool** on the home page, and drag the original post into a chat when you write.

A Weibo post that hits the trending list is often only a few lines long. What pushes it up is the thousands of comments underneath: people who relate, people who push back, people asking "so what am I supposed to do?" When you scroll past it you think there's a piece in it. Two days later all you remember is that it was big. You can't say which angle made it work, or what most commenters actually cared about.

Breaking down a hot post means looking at those two things separately. Decompose handles the post itself: the angle it picked and how its few lines are ordered. A chat handles the comments: where readers' feelings landed. Put them side by side and you don't just have "this topic is hot," you have a topic with an angle and real reader reactions behind it. Saving the post is the first step of building a material library; pulling out the angle and the mood is the second.

## Who it is for

* Creators who follow the news cycle and want to know which angle made a post work, not just which keyword was trending.
* Writers and content operators covering society, consumer issues or work life who need to turn reader sentiment into topics.
* Anyone who wants to collect hot posts over a few weeks and compare which kinds of angle keep taking off.

## How to use it

![Three steps to turn a hot Weibo post into a topic: save it with Add link, click Decompose yourself to get a topic and structure template, then read the public comments in a chat, sum up the mood and note it in the topic pool](https://beav.pro/blog/features/weibo-breakdown-structure-steps-en.webp)

*Decompose the post yourself, hand the comments to a chat, end with a topic of your own.*

1. **Save the post first.*&#x2A; Click &#x2A;*+** next to **Knowledge Base**, choose **Add link** and paste the single post link. Account profiles can't be saved. Details are in [keeping a hot Weibo post and its comments](https://beav.pro/en/blog/features/weibo-save-to-library).
2. **Open it and click Decompose.** To do several hot posts on the same topic at once, select them in the list, open the context menu and confirm the item count and model usage. A batch takes up to 100 items. Saving never starts a decomposition; whether to run one is your call.
3. **Read the result.** Expand it to see a topic, a structure template and the original text, and the topic also shows up in the topic center. Shots, clips and music only appear when the post has a video that's already saved locally, and the docs don't promise Weibo videos get downloaded, so go by whether the entry actually has a video file. The result is also copied to `decompositions/<title>` in the asset library, and the origin panel keeps the post and its author.
4. **Read the comments in a chat.** Send the post's exact link in a chat and say something like "Read the public comments and sum up the main feelings, the questions that keep coming up and where people disagree, with two or three quotes for each." Comments are read on request, and how many come back depends on what's actually returned, which may be fewer than the page shows.
5. **Note the angles in your topic pool.** Ask the AI for a few topics framed as "angle plus reader mood," pick the ones you want, and paste them into the input at the top of the **Topic pool** on the home page. You can paste several at once.

![A hot Weibo post split into four things to look at: angle, mood, open questions and disagreement, each marked as coming from the decomposition or from a chat summary of the comments, with what your topic keeps](https://beav.pro/blog/features/weibo-breakdown-structure-angles-en.webp)

*Illustration. Keep track of what came from Decompose and what came from a chat answer.*

These four are a way of reading the post. You put them together yourself from the decomposition and the chat answers; they aren't conclusions Beav hands you.

**The angle: how it gets into the topic.** The topic and structure template from Decompose help you see what the post is really about. "Young people don't want to work overtime" can be a personal rant, a cost breakdown or a single pointed question. Check the original for how the first line grabs you and what order the rest follows, and write the angle down.

**The mood: what people are angry about or nodding along to.** This one comes from the chat summary of the comments. Ask the AI to separate out sympathy, anger and resignation, with quotes for each. The feeling with the most weight tells you the angle hit a nerve, and the words people use are often the best words for your own headline.

**Open questions: what readers still want to know.** Comments that keep asking "so what do I do?" or "does anyone know\...?" point to things the post didn't answer, which is the easiest place for your piece to stand out.

**Disagreement: what each side is arguing.** For a divisive post, ask the AI to list the main reasons on each side. Your piece can take one side or lay both out clearly.

**Compare several.** One post might have just caught the right moment. Once you've decomposed five or six hot posts on the same topic, drag them into a chat together and ask: "How do these angles differ? Which ones drew the strongest feelings in the comments?" The angles that keep showing up are the ones worth working on. If you want to do the same with RedNote notes, see [analyzing RedNote comments](https://beav.pro/en/blog/features/xiaohongshu-comment-insights).

**Make it your own.** In a chat, open the knowledge base or asset library in the right workspace, drag the decomposed post onto the input box, and say which angle you want to borrow and what your own view and experience are. Or click **AI rewrite** at the top right of the item, add your requirements and send it yourself. You're learning the angle and the structure, not copying the post. Ask before quoting the original or the comments, and before writing about a news event, check the original post and reliable sources.

**What uses quota?** Saving a Weibo post with **Add link** goes through the capture service and uses quota by its rules. Decomposition uses model quota, and a batch asks you to confirm first. Reading a specific single post in a chat doesn't bring up a credit confirmation; asking the AI to search a trending term and read related posts one by one counts as research, and you'll see a credit prompt before the first batch call.

## How it compares with the usual ways

|                   | Handwritten notes                                    | Pasting into a document and highlighting     | Asking a general AI to summarize          | Beav Decompose plus reading comments in a chat                                                                 |
| ----------------- | ---------------------------------------------------- | -------------------------------------------- | ----------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| Strength          | Thinking while you write gives the sharpest judgment | Post and screenshots in one place to mark up | Quick, easy to ask follow-ups             | Post structure and comment summary kept apart, with the source                                                 |
| What you get      | Your own notes                                       | A marked-up document                         | A summary that usually stays in that chat | A topic (added to the topic center), a structure template, the original; the comment summary lives in the chat |
| Comments          | Scroll through them yourself                         | Paste in a few                               | You have to paste them in first           | Send the post link and have public comments read on request                                                    |
| Comparing several | Flip through notebooks                               | Switch between documents                     | Paste everything again each time          | Drag several items into one chat                                                                               |
| Cost              | Free, but slow                                       | Free, but slow                               | Per each provider's terms                 | Capture quota to save, model quota to decompose                                                                |

Scrolling the comments and taking notes yourself gives you the truest feel for a topic, and deciding whether a trend is worth chasing is still your call. For one post you need right now, pasting a few comments into a general AI is plenty. Beav fits the long game: the posts, their decompositions and their sources stay in one library, the comments can be read again whenever you need, and once you have enough you can look for patterns.

## Limits and notes

* **Decomposition is manual only.** Saving and phone submission never start one, and shared spaces don't offer Decompose.
* **Comment mood isn't decomposition output.** Decompose looks at the post only. Comments are read on request in a chat, the summary is the AI's answer, and coverage depends on what's returned.
* **Text-only posts have no shots or music.** Those only appear when the post has a video saved locally, and Weibo videos aren't guaranteed to be downloaded.
* **The structure template and the mood summary are both model-generated.** Check them against the post and the comments before you rely on them.
* **Learn the angle, don't take the content.** The post and the comments are other people's words. Credit the source when you cite, and ask before republishing. Beav never posts for you.

## Next steps

* To go all the way from saving and decomposing to a finished rewrite, read [saving, breaking down and rewriting Weibo posts](https://beav.pro/en/blog/features/weibo-save-breakdown-rewrite).
* For managing the topics you pull out and starting on them, read [where content ideas should live](https://beav.pro/en/blog/features/topic-pool). For why collecting matters at all, read the series overview, ["Accumulation Is the Moat"](https://beav.pro/en/blog/features/accumulation-is-the-moat).
* Full reference: [decompose videos and notes](https://beav.pro/en/docs/workflows/collect-to-create#decompose-videos-and-notes) and [have AI read and save in a chat](https://beav.pro/en/docs/workflows/knowledge-sources#have-ai-read-and-save-in-a-chat).

*Applies to Beav desktop 2.9 and later.*
