Name: 用微博的大數據分析預測股票市場 (Predicting the stock market with big-data analysis of tweets)
Uploaded: 2021-01-14T07:14:17.000Z
Duration: 2 min 33 s

進階被動語態

Can tweets about the stock market be ignored as random noise, generated by

在推特上那些自稱交易的意見領袖所

A study by a team of researchers at Rotterdam School of Management, Erasmus University

鹿特丹的管理學院，伊拉斯莫斯大學中的研究團隊

now shows that tweets contain useful information that can be used

發現推特中有能夠用來預測短、長期股票市場

to predict stock market developments in the short and long term.

This discovery may eventually help investors make better decisions.

這個發現最後能夠幫助投資人做出更有利的選擇

Back to around 2014, The Associated Press Twitter account got hacked

大概在 2014 年，美聯社 (The Associated Press) 的推特帳號遭到駭客入侵

and a fake tweet sent out, to say, well, Barack Obama was injured.

As a result of this fake tweet the stock market went down for 1% for Dow Jones index.

這個假推特消息使股市的道瓊指數跌了 1%

How much is that? More than 100 billion US dollars got swept out.

而這代表 1千多億美元瞬間蒸發

The focal point of this study is actually to find out whether

there is additional information we can extract out of social media

我們是否能夠在社群媒體上吸取更多資訊

in order to better predict stock market performance.

Perhaps we can extract information that goes

說不定我們找到比新聞媒體報導

above and beyond what has been captured within the public news.

At the very beginning we collected about 21 weeks of tweet data and extracted all the

在前期，我們蒐集了 21 週的推特數據，精選出

information in all the tweets that mentioned a top S&P 100 firm.

關於前百大標準普爾公司的推特資訊

We had to determine the sentiment being expressed in those tweets:

我們觀察推特中所表達的心情：

positive, neutral and negative,  indicating that some investor

正面、中立、負面，指出投資人

wants to buy, keep or sell stocks that they hold for a given company.

想要購買、留住、或是賣出他們的股票

What we demonstrated is, indeed, based on that Twitter information, with the value extracted out of

我們想呈現的是，當然，根據推特上精選出來的資訊，

this tweet information, expressed in sentiment, you can make smarter and

從這些推特中呈現的心情感受，你可以做出更聰明、

better trading strategies and earn excess returns.

更好的交易策略，然後賺取更多報酬

Even when we take into account the transaction costs, as well as the fixed costs for running this exercise,

就算我們將交易成本及固定成本列入這次研究的考量

we can see that there's still excess returns, compared to the market performance.

我們可以發現報酬還是超越一般市場表現

The implication goes way beyond just being in financial industry.

這些資訊的意涵優於金融市場的預測

A lot of what we do and what we say, both in online and offline environment,

很多我們在線上、非線上環境所說的話，

has been digitised. We can learn from this digitised human behavior

都被量化。我們可以從這些被量化的行為得知

how individuals make their decisions, and also firms can learn from

個體如何選擇，企業也能從此得知

this to make better decisions that can target and also personalise

如何做出更好的決策，去瞄準並客製化

their services and product at the individual level