Tag Archives: analysis

tinderbox_dashboard

Data science automates love

Tinder App is nothing new for anybody since most of us slowly accepted it in our lives but it also brings some displeasure. For instance, this guy thought that it can automate the process in the way of an app that decides if you’d like a person and start a conversation.

Continue reading

Challenging users to data science

A problem well known in the data science world is the mismatch between people who have the data and people who know how to use it. On the other hand data scientists complain about the difficulties of the scrapping process and more exact, the difficulties of obtaining the data. For this mismatch Kaggle was created, trying to mediate a connection between data and analysts.

The platform was born on this principles and creates a competition between users which must update solutions to diverse data sets and so to win points, and, in the end, money.

On the other side, the uploader of data gets a number of possible solutions of analysis to his data sets, from which he can choose the most appropriate to his interests.

A very interesting case study, and a powerful demonstration in favor of Kaggle capabilities is the collaboration that the platform has, with NASA and Royal Astronomical Society, in which the challenge was to find an algorithm for measuring the distortions in images of galaxies in order for scientists to prove the existence of dark matter. It seems that within a week from the start of the project, the accuracy of the algorithms provided by NASA, and obtained in studies started back in 1934 and continued to that time was reached. More than this , within three months from the start of the project, an algorithm was provided by a user, that was more than 300% more accurate than any of the previous versions. The whole case study can be found here.

 essentially, the fun thing about Kaggle is that the winners of the competitions are folks around the world with a knack for problem solving, and not always degrees in mathematics. And degrees don’t matter on Kaggle; all that matters is result. 

 

 

Why emotions are important in marketing

I don’t know about you but i haven’t given very much thought of how do i feel the instance that i press the “share” button. I recently found out that i was ignoring a much more important part of online marketing than it seems, and i corrected myself, all because of emotions.

When it comes to what we feel, everything can be expressed as a sum of four basic emotions: happy, sad, afraid and angry, that combine themselves and form a variety of other feelings about which we may or we may not be aware. For better understanding of this we may look at Robert Plutchik’s famous “wheel of emotions” that shows just some of the well known emotional layers.

 

Studies have also revealed that the emotional state that “gets” the most of the likes is happiness, which is normal if we consider that  our first emotional action in life is to respond to our mother’s smile with a smile of our own. Obviously, joy and happiness are hard-wired into all of us, as discovered by the psychoanalyst Donald Winnicott. And because happiness almost never comes as a self sustainable feeling we can see that the top 10 emotions that people have when sharing something are made of positive ones, as studied by Fractl.

top 10

 

More than this Jonah Berger, professor of marketing at the University of Pennsylvania’s Wharton School and author of Contagious: Why Things Catch On, conducted a study from which  he found that an article was more likely to become viral the more positive it was.

 

Of course we shouldn’t neglect that there are also other feelings that may interact with our online behavior.  For instance sadness helps us connect and empathize by producing cortisol, known as the “stress hormone”; and oxytocin, a hormone that promotes connection and empathy. Further research revealed that when we are angry the hypothalamus makes us more stubborn and fear only makes us more desperate to find something or someone to cling on.

Considering all this information is easy to understand the high significance of emotions in marketing, especially when considering that an analysis of the IPA dataBANK, which contains 1,400 case studies of successful advertising campaigns where, campaigns with purely emotional content performed about twice as well (31% vs. 16%) as those with only rational content.

And this is why we can’t underestimate the importance of understanding the science of emotion in marketing!

 

Facebook tomorrow!

There comes a time in each of our lives when we wonder ourselves either from curiosity or from perspective  what is going to be the next big thing, and because this is a blog dedicated to science we are gonna restrict to this area.

Of course we can’t know what is going to be the technology of tomorrow but we are going to tell you what is not going to be: Facebook!  According to Princeton’s engineers facebook it’s very likely to reach to an end in the next few years. They used for the research an epidemiological model, very similar to Gaussian bell but more complex in the way of describing the transmission of communicable disease through individuals. According to the model chosen, called SIR the total number of population equals the sum of Susceptible plus Infected plus Recovered persons. They chose this pattern because is relevant for phenomena with relative short life span, and after that they applied in the case of MySpace and they noticed that it fit almost perfectly.

9T7Sm6a

 

We can easily see in this graph that the decline of facebook has already begun but it’s not as near as expected. Actually we can be sure that we will not exterminate it from our lives sooner than 2018 but also, internet can be a very unpredictable place and no one can exactly determine how it’s going to end.

Also we advise you not to take for granted this study because, as we found out, it was conducted by researchers based in the school’s department of mechanical and aerospace engineering. Not saying that they are not professionals but nevertheless not experts in such social studies.

 

About sentiment analysis

Hello internet,

As you probably know, we deal everyday with data scraping, which is quite challenging, but, from time to time we tend to ask ourselves what else is there, and especially, can we scrap something else other than data? The answer is yes, we can, and today I am going to talk about how opinion mining can help you.

Opinion mining, better known as Sentiment analysis deals with automatically scan of a text and establishing its nature or purpose. One of the basic tasks is to determine whether the text itself is basically good or bad, like if it relates with the subject that is mentioned in the title. This is not quite easy because of the many forms a message can take.

Also the purposes that sentiment analysis can be to analyze entries and state the feelings it express (happiness, anger, sadness). This can be done by establishing a mark from -10 to +10 to each word generally associated with an emotion. The score of each word is calculated and then the score of the whole text.  Also, for this technique negations must be identified for a correct analysis.

Another research direction is the subjectivity/objectivity identification. This refers to classifying a given text as being either subjective or objective, which is also a difficult job because of many difficulties that may occur (think at a objective newspaper article with a quoted declaration of somebody). The results of the estimation are also depending of people’s definition for subjectivity.

The last and the most refined type of analysis is called feature-based sentiment analysis. This deals with individual opinions of simple users extracted from text and regarding a certain product or subject. By it, one can determine if the user is happy or not.

Open source software tools deploy machine learning, statistics, and natural language processing techniques to automate sentiment analysis on large collections of texts, including web pages, online news, internet discussion groups, online reviews, web blogs, and social media. Knowledge-based systems, instead, make use of publicly available resources to extract the semantic and affective information associated with natural language concepts.

That was all about sentiment analysis that TheWebMiner is considering to implement soon. I hope you enjoyed and you learned something useful and interesting.