The words that people use have been found to reflect stable psychological traits, but less is known about the extent to which everyday fluctuations in spoken language reflect transient psychological states. We explored within-person associations between spoken words and self- reported state emotion among 185 participants who wore the Electronically Activated Recorder (EAR; an unobtrusive audio recording device) and completed experience sampling reports of their positive and negative emotions four times per day for seven days (1,579 observations). We examined language using the Linguistic Inquiry and Word Count program (LIWC; theoretically created dictionaries) and open-vocabulary themes (clusters of data-driven semantically-related words). Although some studies give the impression that LIWC’s positive and negative emotion dictionaries can be used as indicators of emotion experience, we found that when computed on spoken language, LIWC emotion scores were not significantly associated with self-reports of state emotion experience. Exploration of other categories of language variables suggests a number of hypotheses about substantive everyday correlates of momentary positive and negative emotion that can be tested in future studies. These findings (1) suggest that LIWC positive and negative emotion dictionaries may not capture self-reported subjective emotion experience when applied to everyday speech, (2) emphasize the importance of establishing the validity of language-based measures within one’s target domain, (3) demonstrate the potential for developing new hypotheses about personality processes from the open-ended words that occur in everyday speech, and (4) extend perspectives on intra-individual variability to the domain of spoken language.
The dialectics of the human nature. We have a psychological tendency to talk about what we lack as a defensive mechanism. That's my few cents after reading Freud.
Seems similar in a way to https://qz.com/1198671/depression-warning-signs-pay-attentio..., which I was really struck by because I am prone to using certain language and did not completely consider how it might reflect or tied to my underlying mental condition beyond obvious “mean word” -> “angry”
I have seen a lot of studies that have performed "sentiment analysis" by counting up positive and negative words. I'm glad they are finally realizing how little sense that makes...
I am not sure what to make of such survey based studies. They are not science and often have lots of issues around experiment design, p-values (181 participants).
I really wish these conferences just go away. Great for the authors to progress their careers but of little or negative value to human kind.
I agree with your sentiment. These types of studies would be fine for discussion amongst people in the field. The problem is the headline is the only thing that will make it to social media and some people will take it seriously.
My own opinion has always been that the majority of people who are happy are too busy doing what makes them happy and not posting it on social media. Yes, they are those who are happy and have time/capacity to genuinely post on social media but I must admit to being a sceptic to most posts purporting constant happiness. Maybe it's just me but we all have ups and downs and that is life.
I don't think this dismissal is quite fair, especially regarding this work being unscientific or having negative value to humanity!
The paper described here isn't survey-based; it actually seems very quantitative compared to other psych papers (they collected audio for "150,000 recordings" and computationally analyzed the data; the survey part sounds more like diary data collection). But even if this was entirely survey-based, it wouldn't necessarily be useless.
I do think that it would be better to cover trends in the literature instead of individual studies, but in this case it seems the paper has important implications for sentiment analysis and computational social science in general. I currently hope conferences don't go away!
This is fundamentally a descriptive statistics question (how do X and Y go together) rather than a causal inference question. Descriptive claims still have value; it is clear that both self-assessed happiness and use of language have omitted causes not explored in this research. If anything, this is mostly useful as an exercise to critique operationalization of emotion as sentiment scores in NLP.
16 comments
[ 102 ms ] story [ 3260 ms ] threadAbstract:
The words that people use have been found to reflect stable psychological traits, but less is known about the extent to which everyday fluctuations in spoken language reflect transient psychological states. We explored within-person associations between spoken words and self- reported state emotion among 185 participants who wore the Electronically Activated Recorder (EAR; an unobtrusive audio recording device) and completed experience sampling reports of their positive and negative emotions four times per day for seven days (1,579 observations). We examined language using the Linguistic Inquiry and Word Count program (LIWC; theoretically created dictionaries) and open-vocabulary themes (clusters of data-driven semantically-related words). Although some studies give the impression that LIWC’s positive and negative emotion dictionaries can be used as indicators of emotion experience, we found that when computed on spoken language, LIWC emotion scores were not significantly associated with self-reports of state emotion experience. Exploration of other categories of language variables suggests a number of hypotheses about substantive everyday correlates of momentary positive and negative emotion that can be tested in future studies. These findings (1) suggest that LIWC positive and negative emotion dictionaries may not capture self-reported subjective emotion experience when applied to everyday speech, (2) emphasize the importance of establishing the validity of language-based measures within one’s target domain, (3) demonstrate the potential for developing new hypotheses about personality processes from the open-ended words that occur in everyday speech, and (4) extend perspectives on intra-individual variability to the domain of spoken language.
"Happy words" is "Positive Emotion Words", and doesn't include "happy".
Since you don't know me, you should dismiss this as an internet rumor.
I really wish these conferences just go away. Great for the authors to progress their careers but of little or negative value to human kind.
My own opinion has always been that the majority of people who are happy are too busy doing what makes them happy and not posting it on social media. Yes, they are those who are happy and have time/capacity to genuinely post on social media but I must admit to being a sceptic to most posts purporting constant happiness. Maybe it's just me but we all have ups and downs and that is life.
The paper described here isn't survey-based; it actually seems very quantitative compared to other psych papers (they collected audio for "150,000 recordings" and computationally analyzed the data; the survey part sounds more like diary data collection). But even if this was entirely survey-based, it wouldn't necessarily be useless.
I do think that it would be better to cover trends in the literature instead of individual studies, but in this case it seems the paper has important implications for sentiment analysis and computational social science in general. I currently hope conferences don't go away!