The headline figures have turned positive. How to operate well next?

If you want to run the headline number, you must first know how the headline article is recommended. The following is quoted from the headline official manual:

In order to let popular content be seen by more users, unpopular content will not occupy too many recommended resources. When articles with headline numbers are recommended, they will be recommended to users who are interested in them in batches. ?

How to understand batch recommendation? The article will first be recommended to a group of users who are most likely to be interested in it (these users' reading labels have the highest overlap with the article labels, and the system determines that they are most likely to be interested in the article. ), the reading data generated by these users will play a decisive role in the next recommendation of articles. The data includes click rate, collection number, comment number, forwarding number, reading rate, page stay time and so on. Among them, the click-through rate has the highest weight. This article, which is easy to understand and attracts many users to click, will naturally be considered more likely to be a good article.

From the above, we can see that the factors that affect headline reading are click rate, collection number, comments number, forwarding number, reading rate, page stay time and so on. , so we should adopt the following four strategies when operating headline numbers:

1, improve the click rate: There are two main factors that affect the click rate of an article. One is whether the title is attractive to users, and the other is whether the picture of the title has a pink effect on the article. For example, the cover picture itself is enough to attract users' attention;

2. Improve the reading rate and page stay time: There are two main factors that affect the reading rate and page stay time, one is the length of the article, and the other is the quality of the article; The shorter the article, the easier it is for users to read, the more exciting the article, and the longer the user stays, which requires us to be concise and clear, and talk less nonsense.

3. Increase the forwarding volume and collection volume: The forwarding volume and collection volume of articles mainly depend on the sharing motivation and collection motivation of users. As for the user's motives are varied, I won't discuss them here.

4. Increase the number of comments: If you want users to participate in comments more, you should first guide them, such as adding words such as "Please leave your opinion" at the end of the article, and secondly, the article itself should have a clear point of view that can arouse users' discussion psychology.

The above four points are the four secrets of operating headline numbers well. If you continue to optimize these important data, you will get more machine recommendations!