Group items tagged

Analyzing the verbs that followed male and female pronouns in 100K stories, the following patterns were observed: 1. Women are more likely to be in the role of victims- "she screams", "she cries", or "she pleads." Men tend to be the aggressor: "he kidnaps" or "he beats". Not all male-oriented terms are negative- many, like "he saves"/"he rescues" are distinctly positive- but almost all are active rather than receptive. 2. There's an old stereotype (that's appeared in works like Game of Thrones and Sherlock Holmes) that "poison is a woman's weapon", and this is supported in our analysis. Female characters are more likely to "poison", "stab", or "kick"; male characters are more likely to "beat", "strangle", or simply "murder" or "kill". Men are moderately more likely to "steal", but much more likely to "rob". 3. Based on this text analysis, a fictional murderer is about 2.5X as likely to be male than female, but in America (and likely elsewhere) murderers are about 9X more likely to be male than female. This means female murderers may be overrepresented in fiction relative to reality. David Robinson, the data scientist who ran the text analysis, offers these questions for future research: 1.Is the shift stronger in some formats or genre than another? We could split the works into films, novels, and TV series, and ask whether these gender roles are equally strong in each. 2. Is the shift different between male- and female- created works? 3. Has the difference changed over time? Some examination indicates the vast majority of these plots come from stories written in the last century, and most of them from the last few decades (not surprising since many are movies or television episodes, and since Wikipedia users are more likely to describe contemporary work). 4. I'd also note that we could expand the analysis to include not only pronouns but first names (e.g. not only "she tells", but "M

Members of Congress are often criticized for what they do - or rather, what they don't do. But what about what they say and, more specifically, how they say it? It turns out that the sophistication of congressional speech-making is on the decline, according to the open government group the Sunlight Foundation.

Here's a follow-up on the same study, examining the speech of Hawaii's senators and representatives: http://www.staradvertiser.com/news/breaking/157017545.html?id=157017545. U.S. Sen. Daniel Akaka speaks at a college sophomore level, according to an analysis of his speeches by the Sunlight Foundation, a Washington group that pushes for government transparency. The analysis ranks Akaka in the top five among members of Congress for his use of longer sentences and more complex words. U.S. Sen. Daniel Inouye isn't far behind. His speeches use words and sentences on the level of a college freshman. U.S. Rep. Mazie Hirono speaks at the level of a high school senior, while U.S. Rep. Colleen Hanabusa's speeches are at the high school freshman level, according to the study. Of course, longer sentences and more complex vocabulary use don't necessarily make for better communication, nor indicate effectiveness in re: serving one's constituents.

gives overview of lots of websites and software available for language analysis

Novelist Kurt Vonnegut once opined, "There is no reason why the simple shapes of stories can't be fed into computers. They are beautiful shapes." Thanks to new text-mining techniques, this has now been done. Researchers at the University of Vermont's Computational Story Lab have analysed over 1,700 English novels to reveal six basic story types - you could call them archetypes - that form the building blocks for more complex stories. They are: 1. Rags to riches - a steady rise from bad to good fortune 2. Riches to rags - a fall from good to bad, a tragedy 3. Icarus - a rise then a fall in fortune 4. Oedipus - a fall, a rise then a fall again 5. Cinderella - rise, fall, rise 6. Man in a hole - fall, rise The researchers used sentiment analysis to get the data - a statistical technique often used by marketeers to analyse social media posts in which each word is allocated a particular 'sentiment score', based on crowdsourced data. Depending on the lexicon chosen, a word can be categorised as positive (happy) or negative (sad), or it can be associated with one or more of eight more subtle emotions, including fear, joy, surprise and anticipation. For example, the word 'happy' is positive, and associated with joy, trust and anticipation. The word 'abolish' is negative and associated with anger. Do sentiment analysis on all the words in a novel, poem or play and plot the results against time, and it's possible to see how the mood changes over the course of the text, revealing a kind of emotional narrative. While not a perfect tool - it looks at words in isolation, ignoring context - it can be surprisingly insightful when applied to larger chunks of text

This JSTOR article breaks down and analyzes Abraham Lincoln's famous speech: The Gettysburg Address. Thought to be one of the greatest speeches of all time, The Gettysburg Address helped change public speaking and rhetoric into its modern version. Since the speech is so short, this analysis can examine every single sentence and break down the rhetoric of it. For example, the publication breaks down how Lincoln addresses the past, present, and future in ten sentences.

Employees carrying out an insider attack at work can be identified from the language they use in emails, according to psychologists. The Lancaster University study found that an analysis of the email language of employees within an office environment managed to identify 80 to 90 per cent of those actively stealing confidential information and passing it to a provocateur. Their analysis found that the attackers were much more self-focused, using words like "me," "my" and "I" and they used more negative language compared with typical co-workers. They also found that employees conducting an insider attack reduced the extent to which they mimicked the language of their co-workers. This reduction in mimicry, which suggests an inadvertent social distancing by the attackers, increased over time, such that by the end of simulation, it was possible for the researchers to use the combined metrics to identify 92.6% of insiders.

text analysis tool for detecting deception

This study was conducted in a repeated-measured design; therefore, a paired sample t-test was used for the analysis. An alpha level of .05 was used for the analysis. The independent variable was the type of music played at two different levels of intensity: high intensity and low intensity.

lively analysis of the role of pronouns in English--this writer gives you a glimpse of what it's like to be setting up experiments in psycholinguistics

allows you to enter your twitter handle and have your tweets fed through a language analysis program for psychological profile (developed by researchers in psychology at UT Austin and University of Aukland).

scroll down to "text analysis tools"

"Computational Linguistics became an open access journal, freely available to all online readers. ... Computational Linguistics is the longest running publication devoted exclusively to the design and analysis of natural language processing systems. From this highly-regarded quarterly, university and industry linguists, speech specialists, and philosophers get information about computational aspects of research on language, linguistics, and the psychology of language processing and performance."

"The results are bad news for universalists: "most observed functional dependencies between traits are lineage-specific rather than universal tendencies," according to the authors. [...] If universal features can't account for what we observe, what can? Common descent. "Cultural evolution is the primary factor that determines linguistic structure, with the current state of a linguistic system shaping and constraining future states." It's important to emphasize that this study looked at a specific language feature (word order)."

"Now, after a computer analysis of three decades of hit songs, Dr. DeWall and other psychologists report finding what they were looking for: a statistically significant trend toward narcissism and hostility in popular music. As they hypothesized, the words "I" and "me" appear more frequently along with anger-related words, while there's been a corresponding decline in "we" and "us" and the expression of positive emotions."

a clearly written online textbook

A very interesting and amusing presentation. From the abstract (http://nwav40.georgetown.edu/262.docx.pdf): "I use co-occurrences of words and emoticons to (i) develop a taxonomy of the affective stances Twitter users take, and (ii) characterize the meanings and usage of their emoticons. ... It's reasonable to ask what emoticons themselves mean and reversing the direction of analysis shows how emoticons pattern across words. ... Emoticons with noses are historically older. ... this means that people who use old-fashion noses also use a different vocabulary ... affect and word choice both create and reflect social characteristics like age and gender."

An analysis of 95,000 words Mr. Trump said in public in the past week reveals powerful patterns in his speech which, historians say, echo the appeals of demagogues of the past century.

This is about the "Mozart effect" and if it does indeed help babies become more intelligent by listening to classical music at a young age.

This BBC article notes how media totally misconstrued the modest results reported by the original UC Irvine study, which found that students who listened to Mozart did better at tasks where they had to create shapes in their minds. These students had stronger performance on spatial tasks: specifically, looking at folded up pieces of paper with cuts in them and predicting: how they would appear when unfolded. This effect, however, was sadly temporary: about fifteen minutes. A subsequent meta-analysis of sixteen different studies confirmed that listening to music does lead to a temporary improvement in the ability to manipulate shapes mentally, but the benefits are short-lived and it doesn't make us more intelligent. In 2010 a larger meta-analysis of a greater number of studies again found a positive effect, but that other kinds of music worked just as well, provided that listeners enjoyed what they were listening to. The article concludes that what's crucial in performance is "cognitive arousal": getting your brain more alert, whether it's through music, a Starbucks frappacino, or shooting hoops.

The Stanford Literary Lab is a research collective that applies computational criticism, in all its forms, to the study of literature. Check out their pamphlets to read more about their various literary projects, including "The Emotions of London", "The Language of World Bank Reports."

Explanation and analysis of Introspective Self-Talk study by Senay, Albarracin, Noguchi