What is sentiment? 12-24

What is sentiment?

Sentiment is the tone of voice in which a particular document was written. 

We as humans have usually have no problems determining the sentiment of documents. As we read a text we just know whether it's positive or negative. We've learned that certain words are indicative of a positive sentiment. These are for example words such as good, grand or hero. Other words like terrible, bad or violent are clearly indicative of a negative sentiment. And even when it comes to sarcasm like "go read the great book" we know this is negative for the movie that was reviewed. How different is this for computers that take everything literally.

However, we as humans are limited in that we cannot read and score that many documents in a day. 

It's difficult to get to the big picture really fast. For this we need computers.

How do software programs such as BuzzTalk determine sentiment?

Teams of linguists have created lists of words that correspond with a certain sentiment. 

Each word has a 'force' since for example 'great' is more positive than 'good'. Phrases that match the list are scored with a number between -9 and +9. When the program has reached the end of the document and tagged all the relevant words you can calculate the average score. This average score corresponds to the tone of the document.

Now, this is not all that BuzzTalk does in relation to sentiments but we'll come back to that at a later moment.

How can companies use automated sentiment analysis?

Suppose you've started a big marketing campaign to increase your brand awareness. 

You can use sentiment analysis to determine the public's response to your brand. Are they talking about you? Is their response positive or negative and if negative... how negative and why.

You need to know this kind of information so you can adjust your campaign. 

Also you want to know whether these were marketing dollars well spent.

Since BuzzTalk uses effective sentiment tagging you can easily analyze large amounts of publications on the web. 

We as humans can spot patterns and trends, which would not be possible when we read and analyze only a small portion of the web.

View at the original source

How Twitter takes business intelligence & market research to new heights 12-08

How Twitter takes business intelligence & market research to new heights

If you believe in the Mayan Calendar our world is going to end this year. 

However, if you believe we will still be there you may want to have some better means of predicting the future.

The web has come to reflect the world

Twitter has become very popular in the marketing world because of the potential it provides for viral marketing and webcare.

 Because of it's enormous reach, Twitter is increasingly used by PR and news organizations to filter news updates through the community. Also Twitter is used to advertise products and services and to communicate news to stakeholders.

However, while monitoring of social media is not new, seeing into the future using social media is sizzling hot.

It takes social media from the marketing department upwards to the executive level where business intelligence is needed to support decisions.

Several scientists have conducted research into how we can use big data such as the massive amounts of Tweets and other publications to make reliable predictions about the future. 

Their thought is that social media can be construed as a form of collective wisdom.

Earlier we mentioned the article by Johan Bollen et al. in which he and his team used Twitter to predict the stock market. In this blogpost we'll feature the research done by Asur & Huberman of the Social Computing Research Group at HP Labs who, just like Bollen, used social media conversations as market predictor, only this time for box-office revenues.

The economics of attention: Predicting the future with social media

Asur & Huberman used the chatter from Twitter to forecast box-office revenues for movies. 

The reason for this is that the topic of movies is of considerable interest among Twitter users and real-world outcomes can easily be observed. Their hypothesis was that movies that are well-talked about will also be well-watched. As attention is scarce it's logical to assume that the movie getting attention online will get attention and consumption offline.

They looked at 24 movies and considered 2.89 million tweets from 1.2 million different users. 

Using this data they constructed a linear regression model based on the tweet rate. Tweet rate is defined as the number of tweets for a specific movie divided by the time in hours. On basis of the rate at which people are tweeting they were able to project the revenue the movie was going to make two weeks ahead.

Once the movie opened they did a sentiment analysis of how people reacted with movies they saw to make even more accurate predictions. For this they used the P/N ratio which is the ratio of positive tweets to negative tweets.

Now why is HP studying social media?

Bernardo Huberman explains it in this video by Social Media Examiner:

Companies that use social media for business intelligence

What these scientific research teams are doing is all very sophisticated. 

But now businesses can tap into the wealth of online data and forward-looking insights.

Another example to inspire you is IBM. IBM used big data, specifically social media analysis, to predict women's heel heights. Independent technology analyst Carmi Levy says: "I'm surprised more companies haven't jumped the social media bandwagon. It's ripe for the picking. All this unstructured data is social media intelligence". IBM thinks the same logic could be applied to other industries.

In general from the way people are paying attention you can actually predict the success of your ideas. 

This has a wide range of applications from businesses (predicting product success) to even political (predicting elections).

View at the original source