上星期對 steemit cn版的帖子跟留言數據做了一個文本分析(https://steemit.com/cn/@rayccy/cn-2017-07-01-2017-07-09-what-is-the-most-mentioned-in-cn-tagged-posts-in-the-last-week)，製成了文字雲。今天我又拿了過去一星期的數據，再進行同一種分析，看看大家討論的有什麼分別：
在上次的數據中，Chinese、Thank、Strong這些字出現率很高，這次我就把它們從分析中去除，讓其他結果更清晰。不過跟上次的結果比較，其實大家討論的也沒有太大改變，主要還是關於旅行 (travel)、比特幣、食物 (food)跟小說。
看來應該試試看對於收集到的數據進行一些另外的分析，看看會不會發現到其他有趣的東西！
Last week I conducted a text analysis based on CN-tagged posts and comments (https://steemit.com/cn/@rayccy/cn-2017-07-01-2017-07-09-what-is-the-most-mentioned-in-cn-tagged-posts-in-the-last-week) and made a word cloud. Today I did another one based on the new weekly data and see if there is any difference in what is being discussed. (Result as in the above picture)
In the data last time, words like "Chinese", "Thank" and "Strong" appeared very frequently and are removed in the analysis this time, so as to make the other frequent words more prominent in the result. However, it seems like there hasn't been much change in what's frequently discussed here. Travel, Bitcoin, food and novel remain the hot words!
As data is available, maybe I should try some other types of analyses and see if I have better luck finding more interesting data insights!
我觉得这结果可能还有一点改进的余地
比如说我在一个帖子中各种堆砌同一个关键词，那么是不是就可以把这个关键词做成最大个了？
这个能否想办法避免呢？
對啊，現在的演算法會出現你說的這個問題，需要解決的話要把演算法整個改掉，這部份我還沒有想好怎樣改才比較有效率
其實結果還有其他可以改善的地方，比如現在中英混雜的情況下，英文關鍵字只能出單字而不能出詞語；而且停止詞的列表還未夠完善
所以我想在想到怎樣改變演算法之前先試試其他比較好做的分析好了
謝謝你的意見喔~ :D
Congratulations! This post has been upvoted from the communal account, @minnowsupport, by rayccy from the Minnow Support Project. It's a witness project run by aggroed, ausbitbank, teamsteem, theprophet0, and someguy123. The goal is to help Steemit grow by supporting Minnows and creating a social network. Please find us in the Peace, Abundance, and Liberty Network (PALnet) Discord Channel. It's a completely public and open space to all members of the Steemit community who voluntarily choose to be there.
If you like what we're doing please upvote this comment so we can continue to build the community account that's supporting all members.