Data Mining Reveals the Six Basic Emotional Arcs of Storytelling - Politics Forum.org | PoFo

Wandering the information superhighway, he came upon the last refuge of civilization, PoFo, the only forum on the internet ...

Discuss literary and artistic creations, or post your own poetry, essays etc.
Forum rules: No one line posts please.
#14699960
Scientists at the Computational Story Laboratory have analyzed novels to identify the building blocks of all stories.

by Emerging Technology from the arXiv July 6, 2016

Back in 1995, Kurt Vonnegut gave a lecture in which he described his theory about the shapes of stories. In the process, he plotted several examples on a blackboard. “There is no reason why the simple shapes of stories can’t be fed into computers,” he said. “They are beautiful shapes.” The video is available on YouTube.

Vonnegut was representing in graphical form an idea that writers have explored for centuries—that stories follow emotional arcs, that these arcs can have different shapes, and that some shapes are better suited to storytelling than others.

Vonnegut mapped out several arcs in his lecture. These include the simple arc encapsulating “man falls into hole, man gets out of hole” and the more complex one of “boy meets girl, boy loses girl, boy gets girl.”

Vonnegut is not alone in attempting to categorize stories into types, although he was probably the first to do it in graphical form. Aristotle was at it over 2,000 years before him, and many others have followed in his footsteps.

However, there is little agreement on the number of different emotional arcs that arise in stories or their shape. Estimates vary from three basic patterns to more than 30. But there is little in the way of scientific evidence to favor one number over another.

Image

Today, that changes thanks to the work of Andrew Reagan at the Computational Story Lab at the University of Vermont in Burlington and a few pals. These guys have used sentiment analysis to map the emotional arcs of over 1,700 stories and then used data-mining techniques to reveal the most common arcs. “We find a set of six core trajectories which form the building blocks of complex narratives,” they say.

Their method is straightforward. The idea behind sentiment analysis is that words have a positive or negative emotional impact. So words can be a measure of the emotional valence of the text and how it changes from moment to moment. So measuring the shape of the story arc is simply a question of assessing the emotional polarity of a story at each instant and how it changes.

Reagan and co do this by analyzing the emotional polarity of “word windows” and sliding these windows through the text to build up a picture of how the emotional valence changes. They performed this task on over 1,700 English works of fiction that had each been downloaded from the Project Gutenberg website more than 150 times.

Finally, they used a variety of data-mining techniques to tease apart the different emotional arcs present in these stories.

The results make for interesting reading. Reagan and co say that their techniques all point to the existence of six basic emotional arcs that form the building blocks of more complex stories. They are also able to identify the stories that are the best examples of each arc.

The six basic emotional arcs are these:

A steady, ongoing rise in emotional valence, as in a rags-to-riches story such as Alice’s Adventures Underground by Lewis Carroll. A steady ongoing fall in emotional valence, as in a tragedy such as Romeo and Juliet. A fall then a rise, such as the man-in-a-hole story, discussed by Vonnegut. A rise then a fall, such as the Greek myth of Icarus. Rise-fall-rise, such as Cinderella. Fall-rise-fall, such as Oedipus.

Finally, the team looks at the correlation between the emotional arc and the number of story downloads to see which types of arc are most popular. It turns out the most popular are stories that follow the Icarus and Oedipus arcs and stories that follow more complex arcs that use the basic building blocks in sequence. In particular, the team says the most popular are stories involving two sequential man-in-hole arcs and a Cinderella arc followed by a tragedy.

Of course, many books follow more complex arcs at more fine-grained resolution. Reagan and co’s method does not capture the changes in emotional polarity that occur on the level of paragraphs, for example. But instead, it captures the much broader emotional arcs involved in storytelling. Their story arcs are available here.

That’s interesting work that provides empirical evidence for the existence of basic story arcs for the first time. It also provides an important insight into the nature of storytelling and its appeal to the human psyche.

It also sets the scene for the more ambitious work. Reagan and co look mainly at works of fiction in English. It would be interesting to see how emotional arcs vary according to language or culture, how they have varied over time and also how factual books compare.

Vonnegut famously outlined his theory of story shapes in his master’s thesis in anthropology at the University of Chicago. It was summarily rejected, in Vonnegut’s words, “because it was so simple, and looked like too much fun." Today he would surely be amused but unsurprised.

Ref: arxiv.org/abs/1606.07772: The Emotional Arcs of Stories Are Dominated by Six Basic Shapes

https://www.technologyreview.com/s/6018 ... rytelling/
#14700106
Well it is too simple, because all they've "found" here is that every possible story shape has been used, i.e.,

rise-rise-rise => steady rise
rise-rise-fall => rise then fall
rise-fall-rise => cinderella
rise-fall-fall => rise then fall
fall-rise-rise => rags to riches
fall-rise-fall => oedipus
fall-fall-rise => rags to riches
fall-fall-fall => steady fall

which essentially says nothing at all.
#14700336
No, this opens up a lot because all they did was associate positive or negative association with particular word choice in their sentiment analysis, but in the future this model can become much more complex. For example, you could use word correlation with basic emotions as has been done using visual data to gain a deeper understanding of the emotional content of natural language. For example, perhaps contrasting sentiment analysis between text, audio, and video sources can indicate deception or one could analyze great works by how they appeal to the total range of emotions and the basic emotions from which they derive. We can create geometric representations of emotional states and show whether or not there are functors connecting these states to sentiment analysis, facial motion, diet, nutrition, sleep, drug use, a particular medication, etc. This could be used in prediction of sentiment for example with recording of therapy sessions or courtroom transcriptions. Eventually this kind of sentiment analysis could be applied to audio recording for example putting more weight or words that are spoken with louder volume or with greater frequency. All of this data could also be used to create better ai for customer interaction or to create a "virtual socrates" personal assistant to alter your mood for your benefit. THis can be tied to network analysis in social media to analyze the dynamics of social networks for example how word usage affects group cohesion and when breaks in social networks occur. This is just the very beginning.
Last edited by Ummon on 11 Jul 2016 00:00, edited 1 time in total.
#14700341
Ummon wrote:No, this opens up a lot because all they did was associate positive or negative association with particular word choice in their sentiment analysis, but in the future this model can become much more complex. For example, you could use word correlation with basic emotions as has been done using visual data to gain a deeper understanding of the emotional content of natural language. For example, perhaps contrasting sentiment analysis between text, audio, and video sources can indicate deception or one could analyze great works by how they appeal to the total range of emotions and the basic emotions from which they derive. We can create geometric representations of emotional states and show whether or not there are functors connecting these states to sentiment analysis, facial motion, diet, nutrition, sleep, drug use, a particular medication, etc. This could be used in prediction of sentiment for example with recording of therapy sessions or courtroom transcriptions. Eventually this kind of sentiment analysis could be applied to audio recording for example putting more weight or words that are spoken with louder volume or with greater frequency. All of this data could also be used to create better ai for customer interaction or to create a "virtual socrates" personal assistant to alter your mood for your benefit. This is just the very beginning.


You need to come back down to Earth.
#14700348
Similar methods are already being used to "Using category theory to assess the relationship between consciousness and integrated information theory" with electrocardiogram data as a proxy for the neural correlates of consciousness. Perhaps you just don't understand and if so the problem is hardly my own.
#14700361
This example is a convincing demonstration of why "big data" analysis is pretty worthless when applied to the arts. Barbara Tuchman in her book on historiography described much the same impression in reference to a study on the origins of the First World War:

B. Tuchman wrote:For instance, in a
quantification study of the origins of World War I which I
have seen, the operators have divided all the diplomatic
documents, messages, and utterances of the July crisis into
categories labeled “hostility,” “friendship,” “frustration,”
“satisfaction,” and so on, with each statement rated for
intensity on a scale from one to nine, including fractions.
But no pre-established categories could match all the
private character traits and public pressures variously
operating on the nervous monarchs and ministers who were
involved. The massive effort that went into this study
brought forth a mouse— the less than startling conclusion
that the likelihood of war increased in proportion to the rise
in hostility of the messages.
Quantification is really only a new approach to the old
persistent effort to make history fit a pattern, but reliable
patterns, or what are otherwise called the lessons of history,
remain elusive.


The examples by non-historians that I have seen attempting similar "big data" projects have been equally fruitless and obvious. Will it surprise any writer, student of Joseph Campbell or Carl Jung, that there are "archetypes in literature"? Surely the effort wasted in this analysis could be better spent demonstrating that our ego-states are subjective experiences constructed as evolutionary survival mechanisms or what have you (as the link provided above seemed to indicate), or better help form traffic patterns for large urban intersections or something. I remain unconvinced that there is any value applying these methods to artistic endeavours, except perhaps to satisfy the quantifier's need to quantify and taxonomise. Effectively, this kind of effort speaks to the belief that economic reductionism cannot be refuted for it relies firmly, it is believed, on objective data.

http://www.ted.com/talks/jean_baptiste_ ... of_history?

http://www.ted.com/playlists/56/making_ ... _much_data?

The above videos are by two engineers who are attempting to produce some of the same "big data" analysis of art and history with the expected dull and uninteresting results. I encourage you to review both videos, which I think will further convince you what an enormous waste of time these efforts are, and indeed, how they reflect our civilization's overwhelming trust in mathematical and engineering problem solving, even when it does not produce useful results for the field of study.

It is startlingly obvious that what is occurring is that engineers are beginning to rediscover that history in fact exists and is important, but naturally, they are not trained nor prepared to appreciate it. The result is this embarrassing flaying about as they attempt to apply mathematical models and quantitative analysis to history, with its resulting dismal failure predictable to anyone familiar with, say, Robert Mcnamara and the efforts to control the Vietnam War, the infamous Body Counts, for example.

EU is not prepared on nuclear war, but Russia,[…]

It is implausible that the IDF could not or would[…]

Moving on to the next misuse of language that sho[…]

There is no reason to have a state at all unless w[…]