Language Analysis Across Contexts: A Dialogue Between Forensic Linguistics and Psychology — A Rejoinder to Hunter & Grant (2025)

Before I dive into my thoughts, I want to openly acknowledge my longstanding involvement with the Linguistic Inquiry and Word Count (LIWC) software. I’ve been deeply engaged in its development and daily operations for well over a decade at this point in my life, ranging from (but hardly — and I mean hardly — limited to) continual development/improvement of the LIWC dictionary to driving major updates like LIWC-22. Although I use a fairly wide variety of NLP methods and don’t particularly consider myself a “LIWCian,” my close association with LIWC does color my perspectives. So, as you read on, please consider my insights with an understanding of this background.

Hunter and Grant’s recent critique raises some good questions about LIWC’s applicability in forensic and security contexts. Their observations highlight areas where care and context are necessary when using LIWC and, really, any type of computational tool. While I believe some of their conclusions overstate, or perhaps misplace, LIWC’s limitations1, their paper opens an opportunity to reflect on how we approach language analysis, particularly in high-stakes domains like security and extremism. I have not had any dialogue with the authors of the critique. My hope is that this post will come across as constructive rather than critical, collaborative rather than defensive. But, as we all know, language is complicated, and your interpretation may differ drastically from my intent.

Continue reading…

RIP #8: Approach versus Avoidance

(Originally posted February 5, 2024)

Psychology, as a discipline, tends to go through waves of “big” and “small” thinking. Whenever it swings back to the “big” thinking time periods, we often see a return to some of the most basic, foundational questions about what underlies most (and perhaps all) of human psychology. To be even more accurate: all psychology across all members of the animal kingdom.

Over the past 150 years, we can see several periods of serious return to, and departure from, an absolutely key discussion point in the social sciences: Darwinian evolution. You’re all incredibly smart and thoughtful, so I won’t bore you with a ham-fisted retelling of evolutionary theory. But, really, the key talking point of evolutionary theory that we all know is this — in order for a species to survive in the long term, it has to survive in the short term. In practical terms, this means that we are well-served by propensities to avoid or escape harmful or noxious things in our environment, and approach things that are helpful or beneficial in some way. This basic idea is perhaps most often recognized in psychology, in its various forms, by infamous names like “hedonic motivation” or “the pleasure principle.”

Continue reading…

RIP #7: Positivity Offset

(Originally posted January 2, 2024)

New year, new RIP! I hope that everyone has had a wonderful holiday season, and I’d like to kick the year off with something positive. Well, in a manner of speaking, I’d like to kick the year off by talking about positivity itself!

Over the years, I have heard many, many, many times that psychological science is a ridiculously diverse discipline, which is one thing that I absolutely love about the field. Take any given psychological topic, and you can study it through the lens of any number of subdisciplines. Are you interested in studying dating? You can study it through the lens of how romantic partners influence each other (social psych). You can study it by trying to figure out the different ways that people try to find a short- or long-term mate (evolutionary psych). You can study it through how people think about or understand their relationships with others (cognitive psych). You can study how relationships vary across time/space (cultural psych). You can study how relationship styles form and change throughout our lives (developmental psych). The list goes on and on. And that’s just talking about one particular slice of romantic relationships!

Continue reading…

RIP #6: Integration

(Originally posted November 14, 2023)

Here’s the trouble with how we think about measuring abstract psychological things that go beyond the physical processes of nervous system functioning — none of these psychological things are uniform, let alone unified into actual unitary constructs. Much of the time, we treat them as unified “things” for the purpose of actually getting research done. “Happiness” is a thing that we want to measure or influence in some mechanistic way. “Social connections” are things that we want to measure or influence in some mechanistic way. Whatever the construct might be that we’re studying, we have to treat it as a “thing” and operationalize it such a way that we can quantify it through some form of data generation mechanism. We leave it to the hardcore specialists in each of the domains to worry about the details about what the different “pieces” of something like happiness might be. Life is too short to worry about the little nuances that might change our fundamental interpretation of what we mean by “happiness” — we’re trying to operate at a functional, human level, right?

Zooming out to the human level, Robert Kurzban uses a “smartphone apps” metaphor to describe human psychology. To paraphrase, he describes the human mind as a smartphone that is running lots of apps concurrently. Some of them may interact, but really, there is no top-level “governor” that ensures that they are logically unified in a purposeful way, all of them behaving in a fashion to accomplish a unitary goal. The human mind is just a collection of… apps, each performing different operations and functions to accomplish different goals.

Continue reading…

RIP #5: A Science of Behavior

(Original posted October 23, 2023)

I know, I know… you’ve all been sitting around, nothing to do, waiting with baited breath for another psychology paper to read. Wait no more! It’s time for another RIP!

As a bit of history, the fields of social and personality psychology existed for quite a while as totally separate subdisciplines in psychology. And, if you’re unaware, there was a catastrophic fallout between these two subdisciplines in the 1960’s and 1970’s — this is now known as the person-versus-situation debate. I won’t get into specifics here — the important “big picture” point is that social psychology absolutely whomped the crap out of personality psychology, claiming that (at best) personality didn’t matter, with many big-deal scholars going so far as to claim that personality itself doesn’t even exist. Personality, they claimed, was just a byproduct of the situation, and the situation is all that actually matters in shaping and causing variations in human thought, feeling, and behavior.

Now, let’s take a look at the methods favored by these two subdisciplines: in one corner, we have personality psychology, the champ of self-report methods. Personality psychologists were all about asking people to describe themselves and their traits. They’d say, “Hey, tell us about your personality,” and individuals would respond with questionnaires and surveys. It was like peeking inside their minds and hearts to understand their internal characteristics. In the other corner, we’ve got social psychology, the master of quantifying behavior. These folks were less interested in what people thought about themselves and more intrigued by what they actually did. They’d set up experiments and observations, watching how folks behaved in various situations. It was all about actions, not just words.

Continue reading…

Formal Treatment

“But his protest is not likely to be heard. For the prestige of statistics and scientific methodology is enormous. Much of it is borrowed from the high repute of mathematics and logic, but much of it derives from the flourishing state of the art itself. Some statisticians are professional people employed by scientific and commercial enterprises. Some are teachers and pure researchers who give their colleagues the same kind of service for nothing—or at most a note of acknowledgement. Many are zealous people who, with the best of intentions, are anxious to show the nonstatistical scientist how he can do his job more efficiently and assess his results more accurately. There are strong professional societies devoted to the advancement of statistics, and hundreds of technical books and journals are published annually.  

[…]

If we are interested in perpetuating the practices responsible for the present corpus of scientific knowledge, we must keep in mind that some very important parts of the scientific process do not now lend themselves to mathematical, logical, or any other formal treatment. We do not know enough about human behavior to know how the scientist does what he does. Although statisticians and methodologists may seem to tell us, or at least imply, how the mind works—how problems arise, how hypotheses are formed, deductions made, and crucial experiments designed—we as psychologists are in a position to remind them that they do not have methods appropriate to the empirical observation or the functional analysis of such data. These are aspects of human behavior, and no one knows better than we how little can at the moment be said about them.”

Skinner, B. F. (1956). A case history in scientific method. American Psychologist, 11(5), 221–233. https://doi.org/10.1037/h0047662

On Being Interdisciplinary

Just over a decade ago, I left one Ph.D. program to join another. I was working on a lot of traditional questions in Psychology, and approaching them in relatively traditional ways — nothing about it was especially satisfying to me. Well, okay, nothing about it was satisfying at all. But that’s another story. So, I found myself jumping ship, heading down to Texas to pick up a Psychology Ph.D. while working with someone who was, at the time — and, frankly, still is — one of my heroes, both intellectually and personally: Jamie Pennebaker.

I arrived with a solid foundation in traditional psychology — inferential statistics, study design, all the standard tools of the trade. But, very quickly, I realized that those things weren’t as crucial as I thought they would be. Jamie told me to go talk to some folks over in the computer science department and get trained in machine learning. I was deeply hesitant about whether I would be able to actually learn something that sounded so completely alien and complicated. So, I told him point-blank, something along the lines of “I don’t even know what machine learning is.” His response was refreshingly blunt — with a characteristic Jamie smirk, he shrugged and said “Me neither. But you probably should.” And just like that, I found myself plunging into a whole new world.

Continue reading “On Being Interdisciplinary”

RIP #4: Asking Questions

(Originally Posted September 27, 2023)

The weather is getting chilly, we’re all back in the daily grind and — for me — it brings back vivid memories of sitting in old classrooms in various psychology buildings at the beginning of a new school year. Psychology buildings tend to be old and dusty, especially compared to CS buildings — ahh, the aroma of old wooden desks, the faintly vanilla smell of old books, the chilly rooms on grey, windy days, and the narrative, philosophical discussions about how we know anything about “the human condition.”

Most junior graduate students in the social sciences become socialized in the world of actually doing research by having research questions handed to them by their advisors. In psychology, these aren’t so much framed as “problems to solve” so much as “here’s a question that we don’t have an answer to yet. But we expect that the answer will look like either X or Y, because Z theory says so.” And so, we dutifully put together a study to see if, for example, people who are are more “cognitively” egocentric are also more “socially” egocentric, run the study, and subsequently write up the results into a paper that doctors still prescribe as a powerful treatment for insomnia due to its potent narcoleptic effects.

Continue reading…

RIP #3: The Big Five and Life Outcomes

(Originally posted August 30, 2023)

What’s that you say? You’re ready for another RIP? Well, let’s do it!

For RIP #3, I want to share a major paper in personality psychology that (I find) most people outside of personality psych don’t know about — Ozer & Benet-Martinez (2006).

Some of you — especially if you attended the workshop — have heard me talk about nomological networks and, essentially, how we “define” the psychological constructs that we’re studying by triangulating what, precisely, they are related to.

Now, you all have heard over and over (and over, and over, and over) again that the Big Five is really the dominant model of personality. And, when you talk to people who use the Big Five, they’ll often rattle off a huge list of associations/correlates of each of the Big Five. “Oh, extraverts live longer, are happier, are rated as more attractive…” etc. etc.

How the heck do personality psychologists know all of this stuff? Are they just really good scholars? Did they read a thousand Big Five papers and memorize all of the things that the Big Five correlate with?

Continue reading…