Content uploaded by James Houran
Author content
All content in this area was uploaded by James Houran on Aug 28, 2023
Content may be subject to copyright.
PAGE 335
PAGE 336
Journal of Anomalous Experience and Cognition (JAEX)
Phenomenology of AI-Generated
“Entity Encounter” Narratives1
James Houran Brian Laythe
Integrated Knowledge Systems Institute for the Study of Religious and Anomalous Experience
Abstract: Objective: We used the ChatGPT-3.5 artificial intelligence (AI)-based language program
to compare twelve types of mystical, supernatural, or otherwise anomalous entity encounter
narratives constructed from material in the publicly available corpus of information, and compared
their details to the phenomenology of spontaneous accounts via the Survey of Strange Events (SSE)
and the grounded theory of Haunted People Syndrome (HP-S). Methods: Structured content
analysis by two independent and masked raters explored whether the composite AI-narratives
would: (a) cover each encounter type, (b) map to the SSE’s Rasch hierarchy of anomalous
perceptions, (c) show an average SSE score, and (d) reference the five recognition patterns of HP-S.
Results: We found moderate evidence of a core encounter phenomenon underlying the AI-
narratives. Every encounter type was represented by an AI-generated description that readily
mapped to the SSE, albeit their contents showed only fair believability and low but generally positive
correlations with each other. The narratives also corresponded to below-average SSE scores and
referenced at least one HP-S recognition pattern. Conclusions: Prototypical depictions of entity
encounter experiences based on popular source material certainly approximate, yet not fully
match, the phenomenology of their real-life counterparts. We discuss the implications of these
outcomes for future studies.
Keywords:AI, content analysis, entity encounters, ghostly episodes, HP-S, narrative construction,
phenomenology
Highlights
• ChatGPT can generate prototypical entity encounter narratives with a fair degree of
believability.
• AI-generated encounter narratives with diverse outwardly themes often reference
similar perceptual contents and contextual variables.
• AI-generated encounter narratives do not fully match the phenomenology of real-
life reports as modeled by integrative theory formation using recent psychometric
research.
What is the nature of entity encounters as frequently debated by social and
biomedical scientists? The popular artificial intelligence (AI) program called ChatGPT
gives a surprisingly balanced and thoughtful answer:
As an AI language model, I cannot provide a definitive answer to the
reality of entity encounters since it is a subjective and often controversial
topic. However, it is important to note that many people report having
experienced encounters with entities, such as ghosts, angels, demons,
and extraterrestrial beings.
Some people believe that these encounters are real and provide
evidence of the existence of a spiritual or supernatural realm beyond our
understanding. Others believe that these encounters are simply products
of the human imagination, influenced by cultural beliefs, personal
experiences, and psychological factors.
There is no scientific evidence that definitively proves or disproves the
existence of entities, and opinions on the matter can vary widely
depending on individual beliefs, cultural context, and personal
experiences. It is important to approach these topics with an open mind
and to seek reliable sources of information and support when dealing
with unexplained phenomena (conducted by the authors, March 1, 2023).
Despite the ongoing controversy, qualitative and quantitative research has
revealed several key insights about the phenomenology of encounter experiences.
Phenomenology is the study of the structures of experience and consciousness (Seamon,
2000), which Laythe et al. (2021, p. 198) described as having “macro” and “micro” aspects.
Macro-phenomenology refers to the mediating conditions for the onset or proliferation of
particular altered-anomalous experiences, whereas micro-phenomenology involves the
2023, Vol. 3, No. 2, pp. 335-368
Co pyr i gh t © 2 023 T he Aut h or ( s) CC -BY Lic e ns e
https://doi.org/10.31156/jaex.25124
Jo urn a l of Ano m al o us E x per i en c e an d C ogn iti o n
(JAEX)2023, Vol. 3, No. 2, pp. 335-368
1Address correspondence to: J. Houran, Ph.D., Integrated Knowledge Systems, 7041 Briarmeadow Dr., Dallas, Texas,
USA, 75230, jim_houran@yahoo.com. We thank Damien J. Houran, Cindy Little, Ramsés D'León, and Adrian Ryan for
their assistance. This study was part of a larger project on interactionism and anomalous experiences supported
by the first author’s grant from the BIAL Foundation (bursary #006-2022) for which we express our appreciation.
PAGE 337
PAGE 338
Journal of Anomalous Experience and Cognition (JAEX)
moderation of specific contents or details of the altered-anomalous experiences2. These
nuances are readily exemplified by paradoxes long noted in haunt-type cases, such as
why some people have experiences while others also present do not (i. e., macro-
phenomenology, e. g., Cornell, 2002; Roll, 1977) or why multiple witnesses can perceive
shared experiences differently (i. e., micro-phenomenology, e. g., Jaki, 1999; McHarg, 1973).
Much evidence suggests that entity encounters typically manifest to people with
thin (or permeable) mental boundary functioning, as measured by dissociative
tendencies (Ross & Joshi, 1992), psychological absorption (Lifshitz et al., 2019),
transliminality (Laythe et al., 2018), or a host of other hypnosis-related attitudes or
behaviors (Kumar & Pekala, 2001). We also know that while the general appearance or
meaning of entity encounters often varies with the setting in which the experience occurs
(Evans, 2001; Houran, 2000), the specific perceptual contents tend to be consistent across
experients in two aspects. First, episodes often reference psychological or subjective
experiences (“S,” e. g., apparitions, sensed presences, hearing voices, and unusual
somatic or emotional manifestations) and physical or objective events (“O,” e. g.,
apparent object movements, malfunctioning electrical or mechanical equipment, and
inexplicable percussive sounds like raps or knocks). Second these S/O anomalies
collectively form a probabilistic and unidimensional Rasch scale, that is, a literal “haunt
hierarchy” involving a series of mini entity encounters (Houran et al., 2019a,b).
In other words, there is ostensibly a core encounter phenomenon that presents
much like a syndrome. Particularly, Laythe et al.’s (2021, 2022) grounded theory of Haunted
People Syndrome (HP-S) contends that spontaneous ghostly or entity encounters
recurrently experienced by certain people are an interactionist phenomenon in which
psychophysical stress is a catalyst for altered-anomalous experiences that derive from
thin mental boundary functioning. Experients’ paranormal belief or threat detection
processes encourage these perceptions to be interpreted as the actions of purposeful
agents. Additional experiences then begin to snowball because of attentional- or
confirmation- biases. Succinctly put, HP-S represents somatic-sensory sensitivities
stirred by dis-ease states, contextualized within paranormal belief, and reinforced with
threat-agency detection and perceptual contagion. Table 1 outlines these components
via a checklist of five general recognition patterns.
Table 1
Checklist for Recognition Patterns of Haunted People Syndrome (HP-S)
2We developed our concept of micro-phenomenology independently from Petitmengin et al. (2019), who used
the term to describe their interview method for collecting fine-grained descriptions of lived experiences
associated with various sensorial, emotional, or cognitive processes so that a corpus of accurate data relevant to
a research objective can be gathered. However, both views involve the idea of a “psychological or behavioral
microscope” that distinguishes descriptive elements in a narrative from those related to explanations or
judgments.
2023, Vol. 3, No. 2, pp. 335-368
PAGE 339
PAGE 340
Journal of Anomalous Experience and Cognition (JAEX)
The Present Study
One way to examine the idea of a core encounter phenomenon that can change
in appearance is to search “mainstream consciousness” (i. e., the general public’s
awareness of certain ideas and topics) for prototypical (or archetypal-like3) first-person
narratives involving distinct types of presumably real entities and then assess whether
they exhibit markedly similar themes, structures, and correlates as gauged by the Survey
of Strange Events (SSE: Houran et al., 2019b) and the HP-S model. OpenAI’s advent of the
AI-based language program “ChatGPT” (or Generative Pre-trained Transformer 3) offers
an efficient and topical way to potentially mine such data. There are two versions of this
extremely advanced chatbot: (a) the default GPT-3.5 is less powerful but open access,
whereas (b) the superior GPT-4 is only available via paid subscription and limited use.
Guinness (2023) explained that ChatGPT works by attempting to understand
prompts and then spitting out strings of words that it predicts will best address the
question or task based on the training data. The program was originally trained on
roughly 500 billion “tokens” that allow its language models to assign meaning and predict
plausible follow-on text more easily. Many words map to single tokens, though longer or
more complex words often break down into multiple tokens. On average, tokens are
roughly four characters long. All the tokens come from a massive corpus of data written
by people, including books, articles, and other documents across all different topics,
styles, and genres, as well as an enormous amount of content scraped from the open
internet. This humongous dataset was used to form a deep learning neural network—a
complex, many-layered, weighted algorithm modeled after the human brain—that allows
ChatGPT to learn patterns and relations in the text data and tap into the ability to create
human-like responses by predicting what text should come next in any given sentence.
The program does not work at a sentence level; instead, it generates text of what words,
sentences, and even paragraphs or stanzas could follow. To further refine ChatGPT's
ability to respond to a variety of different prompts, it was optimized for dialogue with a
technique called reinforcement learning with human feedback. Essentially, individual
users created a reward model with comparison data (where two or more model
responses were ranked by AI trainers), so the AI could learn which was the best response.
Based on the above, this language program should aptly fulfil a request to “Tell a
convincing real-life ghost story.” ChatGPT indeed stated in a text session that, “I can
attempt to create a story based on the common themes and details that have been
reported in such encounters.” It might be expected therefore that the macro- and micro-
phenomenology of these AI-narratives will parallel the known features and dynamics of
“real-life” paranormal encounters as documented per Laythe et al.’s (2021, 2022) HP-S
model. Accordingly, we used ChatGPT-3.5 to test four hypotheses:
1. AI-narratives will be generated from believable material in mainstream consciousness.
2. AI-narratives will readily and similarly map to the Survey of Strange Events.
3. AI-narratives will correspond to an average score on the Survey of Strange Events.
4. AI-narratives will reference the five recognition patterns of Haunted People Syndrome.
Method
AI-Narratives
Our selection of entity encounters was derived primarily from Evans’s (1986, 1987,
2001) comparative literature research, and secondarily from quantitative studies of
reported experiences (Houran, 2000; Houran et al., 2019b; Kumar & Pekala, 2001). Table 2
summarizes twelve (12) types of entity encounters considered here, including two
narratives that arguably represent “hidden or disguised” encounter experiences, e. g.,
gang-(or group) stalking (e. g., Lange et al., 2020) and autonomous or “deep” imaginary
companions (e. g., Little et al., 2021). We generated our sample of AI-narratives via a
2023, Vol. 3, No. 2, pp. 335-368
3Cullum et al. (2017) argued that: “Archetypes can be framed as abstract exemplars of classes, conceptual
models linking form and process and/or tacit mental models” (p. 95). Archetype relates here to behavior,
historical psychology, and literary analysis, and more specifically a statement, pattern of behavior, prototype,
“first” form, or a main model that other statements, patterns of behavior, and objects copy, emulate, or “merge”
into. Informal synonyms frequently used for this definition include “standard example,” “basic example,” and
“archetypal example,” mathematical archetypes often appear as “canonical examples.” This contrasts with the
Jungian psychology definition of a collectively inherited unconscious idea, pattern of thought, image, etc.,
universally present in individual psyches.
PAGE 341
PAGE 342
Journal of Anomalous Experience and Cognition (JAEX)
multi-stepped process whereby ChatGPT-3.5 was asked to “Write a convincing account
of a real-life [insert name of entity encounter type here].” This was repeated for all twelve
encounter types. Note that we did not experiment with alternative versions of this
instruction set (e. g., “Write a convincing account of […] as usually reported in the media”).
As a convenient cross-check, we also generated three comparison (or control) AI-
narratives to examine ChatGPT-3.5’s capacity for detailed story-telling as measured by
the word count of the outputs. We settled on three realistic scenarios that likely involved
intense perceptions framed by the elements of surprise or drama, requesting the
language program to produce “convincing real-life accounts of: (a) witnessing a car
accident, (b) having a COVID-19 infection, and (c) seeing the Aurora Borealis for the first
Table 2
Background Descriptions of the Entity Encounter Narratives
time.” The Appendices give sample AI-narratives for an encounter experience (Appendix
A: “ghost sighting’) and a control scenario (Appendix B: “Aurora Borealis sighting”). We
used the control narratives only for a general statistical comparison with the encounter
narratives, so the raters neither saw nor considered them in their analyses. The full set of
AI-narratives used in this study is freely available to interested readers at the Psi Open
Data repository: https://open-data.spr.ac.uk/dataset/chatgpt-generated-entity-
encounter-narratives.
Raters
Content analysis of the AI-narratives was conducted by two individuals of different
backgrounds but with prior experience using our coding materials: (a) one individual is a
Ph. D. level parapsychologist, and (b) the other was a college student and occult
practitioner who actively supports citizen science efforts in anomalistics.
Coding Materials
The Survey of Strange Events (SSE: Houran et al., 2019a,b, 2021) is a 32-item, true/
false Rasch (1960/1980) scaled measure of the overall perceptual intensity (or depth) of
a ghostly account or narrative via a checklist of anomalous experiences inherent to these
episodes (Table 5 lists all the items). The SSE’s Rasch item hierarchy represents the
probabilistic ordering of S/O events according to their endorsement rates but rescaled
into a metric called “logits.” Higher logit values denote items with higher positions (or
greater difficulty) on the Rasch scale (Bond & Fox, 2015). SSE item endorsements sum to
raw scores that are converted to Rasch scaled scores—ranging from 22.3 (= raw score of
0) to 90.9 (= raw score of 32), with a mean of 50 and SD = 10. The Rasch reliability = 0.87,
and higher scores correspond to a greater number and perceptual intensity of anomalies
that define a percipient’s cumulative experience of a ghostly episode, which comprises
an array of different entity encounters. Supporting the SSE’s construct and predictive
validities, Houran et al. (2019b) found that the phenomenology of “spontaneous”
2023, Vol. 3, No. 2, pp. 335-368
PAGE 343
PAGE 344
Journal of Anomalous Experience and Cognition (JAEX)
accounts (i. e., self-reported as sincere and unprimed) differed significantly from control
narratives from “primed conditions, fantasy scenarios, or deliberate fabrication.” That is,
spontaneous ghostly episodes have a specific sequence (or Rasch model) of S/O
anomalies that is distinct from the details of narratives associated with other contexts.
The HP-S Recognition Patterns Checklist (Houran et al., 2023). was used to guide the
raters’ content analyses of the contextual aspects of the various encounter narratives. It
outlines the five recognition patterns of HP-S via seven specific questions that are rated
on four-point Likert scales anchored by “Strongly Disagree” (scored “0”) to “Strongly
Agree” (scored “3”). Raw ordinal scores range from 0 to 21, with higher scores indicating a
greater likelihood of the respective HP-S recognition patterns being present. Table 1 shows
the basic checklist, which references the Revised Transliminality Scale (RTS: Lange,
Thalbourne et al., 2000) and the Rasch version (Lange, Irwin, & Houran, 2000) of Tobacyk’s
(1988, 2004) Revised Paranormal Belief Scale to help users recognize attitudes or
behaviors indicative of thin boundary functioning.
The RTS is a 17-item, T/F, Rasch scaled instrument to gauge the tendency for
ideation, affect, imagery and perception to cross (trans) thresholds (limines) into or out
of consciousness as indexed by experiences like hyperesthesia, fantasy proneness,
absorption, mystical experiences, magical thinking, and others.
In contrast, the Rasch-RPBS is a 26-item, Likert based measure with two subscales
hypothesized to reflect different control issues: (a) “New Age Philosophy” related to a
greater sense of control over interpersonal and external events (e. g., belief in psi) and (b)
“Traditional Paranormal Beliefs” about more culturally-transmitted beliefs about magic,
determinism, and a mechanistic view of the world.
We provided copies of these two instruments to the coders as critical
supplementary information. The Recognition Pattern Checklist is primarily a worksheet
rather than a formal assessment, so no psychometric properties are reported here.
Perceived Authenticity. Each narrative was followed by a one-item global rating of
its face validity scored by each rater on a four-point Likert scale: “This narrative sounds
realistic to me: Strongly Disagree (0), Disagree (1), Agree (2), Strongly Agree (3).”
Procedure
Following Houran et al.’s (2023) procedure in a similar study, we gave the coders
copies of the: (a) twelve AI-narratives in a randomized order, (b) SSE measure, (c) HP-S
Recognition Patterns Checklist, and (d) the global rating of Perceived Authenticity. Each
coder was masked to our hypotheses and the source of the narratives. They worked
independently for three days to code the phenomenology of these accounts by
documenting the presence of specific S/O anomalies via SSE ratings, as well as any
contextual variables presumably associated with the onset or report of those anomalies
via the HP-S Recognition Patterns Checklist (supported by the two belief-boundary
measures noted earlier). Accordingly, each rater returned two completed forms (cf.
Tables 1 and 5).
Analysis
We primarily tested our hypotheses using planned correlational analyses, with p<
.05, two-tailed, as the criterion for significance.
Results
Inter-Rater Reliability
There is debate over which tests best evaluate the interrater reliability of ordinal or
categorical data (O'Neill, 2017), albeit some authorities argue that various statistics
typically lead to the same general conclusion (de Raadt et al., 2021). We decided to use
Cohen’s kappa (ĸ) for the coders’ binary SSE item endorsements, and Spearman’s rho (rs)
for the Likert categories on the HP-S Recognition Patterns Checklist. Table 3 shows a
2023, Vol. 3, No. 2, pp. 335-368
PAGE 345
PAGE 346
Journal of Anomalous Experience and Cognition (JAEX)
moderately strong level of agreement between the raters on most of the presented
details across the twelve narratives in terms of their macro- and micro- phenomenology.
More generally, this outcome supports the capability of citizen scientists for some types
of parapsychological research (cf. Houran et al., 2022; Appendix).
Table 3
Coders’ Averaged Ratings on Contextual and Macro-Phenomenology Variables Across
the AI-Generated Narratives
Note: SSE : Survey of Strange Events, HP-S = Haunted People Syndrome, HP-S 1a = Transliminalilty, HP-S2 = Dis-
ease State, HP-S 3a = Diverse Array of S/O Anomalies, HP-S 3b = Perceptual Flurries Suggestive of Contagion,
HP-S 4 = Interpretations Consisten with Context, HP-S 5 = Threat-Agency Detection
That said, the interrater reliability of the SSE and HP-S Recognition Patterns Checklist
ratings was not even across the AI-narratives. The stories about the Men-in-Black,
Angelic Encounter, and Alien Abduction showed the lowest reliability on SSE ratings, in part
because of discrepancies related to perceptions of non-descript visual images and
recognizable sounds of mysterious origin. On the other hand, the narratives about the
Haunted House, Ghost Story, and Poltergeist Outbreak had the lowest reliability on the HP-
S Recognition Patterns Checklist ratings, mostly because of discrepancies over clear
indications of: (a) dis-ease states at the time of the fictional percipients’ anomalous
experiences, and (b) perceptual flurries characteristic of contagion effects.
Hypothesis 1: AI-Narratives Will Be Generated from Believable Material in the
Mainstream Consciousness
Note that ChatGPT’s claim that it can “…create a story based on the common
themes and details that have been reported in such encounters” implies a sufficiently rich
supply of accessible source material within its training set with which to generate a
composite (or archetypal-like) narrative. As hypothesized, Table 2 shows that the
language program indeed generated a composite account for each of the twelve
specified encounter experiences. The average word count for these narratives (M=
343.40, SD = 29.10) compared favorably to our three control AI-narratives (M= 279.33, SD
= 19.90). However, the average rating of Perceived Authenticity (M= 1.70, SD = .75)
indicated that the encounter narratives only reached a somewhat “fair level of
believability.” Closer inspection revealed that eight narratives about specific entities (e. g.,
tupla encounter) were rated as most believable to the coders, whereas the more generic
accounts (e. g., ghost story) were deemed the least authentic.
Table 4
Spearman Rank-Order Correlations Between the AI-Narrative’s HP-S Characteristics
*=p< .01
Table 4 clarifies that Perceived Authenticity was not associated with a higher Word
Count (rs= -.13, p=.80) but instead with references to Threat-Agency Detection (HP-S
2023, Vol. 3, No. 2, pp. 335-368
PAGE 347
PAGE 348
Journal of Anomalous Experience and Cognition (JAEX)
Recognition Pattern #5) (rs= .81, p< .01) and Paranormal Belief (HP-S Recognition Pattern
#1) (rs= .23, p= .19), as well as the SSE scaled score (or index of perceptual intensity) for
the narrative (rs= .49, p=.08). That is, the experiential context and contents of the
narratives influenced their overall believability more so than the sheer length of the
stories.
Hypothesis 2: AI-Narratives Will Similarly Map to the SSE Measure
The raters reported no problems mapping the S/O descriptions in the AI-
narratives to the SSE’s 32 items, and Table 5 shows the frequency distribution of these
item endorsements. We see that 27 (84%) of the 32 S/O anomalies were present in one or
more of the narratives, whereas the remaining five (16%) were never mentioned.
Additionally, five of the 27 listed anomalies specifically featured in most of the stories (i. e.,
“onset of negative feelings, sensed presences, physical perturbations, sense of
communication with an outside force, and discernible voices or noises”). It is very curious
that the frequency distribution of specific SSE items showed a suggestive correlation (r=
-.32, p= .07) with their logit values. In particular, this result generally aligns to Houran et
al.’s (2019b) benchmark data in that S/O anomalies endorsed more often by experients
occupy lower statistical positions in the Rasch hierarchy (i. e., have lower logit values
indicating they are “easier” or more likely to endorse).
As expected, Table 6 further indicates that there was substantial consistency in the
specific SSE mappings across the various encounter experiences. In fact, 79% of the AI-
narratives showed positive (albeit small to moderate sized) correlations between the
average of the two coders’ discrete ratings across all 32 items on the SSE—with the
strongest correspondence curiously between Men-in-Back encounters and Alien
Abductions (r= 64, p< .05). However, 11 instances (17 %) showed essentially null
correlations, and three correlations were inverse (but small in magnitude). On this latter
point, the greatest disparities in SSE mappings were between encounters involving Angels
vs Poltergeists, Angels vs. Gang-Stalking, and Fairy Sighting vs. Haunted House.
Table 5
Frequency Distribution of Perceptual Contents (Micro-Phenomenology) Across the AI-
Narratives
2023, Vol. 3, No. 2, pp. 335-368
PAGE 349
PAGE 350
Journal of Anomalous Experience and Cognition (JAEX)
Table 6
Correlations Between Coders’ Averaged SSE Item-Level Ratings of the AI-Narratives
Hypothesis 3: AI-Narratives (as Putative Cultural-Level Composites) Will Show
Average SSE Scores
This hypothesis was not supported. The 12 narratives had an average raw SSE
score of 6, which corresponds to a Rasch scaled SSE score of 44.40 (the actual mean SSE
score across the sample was 43.98). Either metric represents a below-average level of
perceptual intensity for a ghostly episode per published norms (Houran et al., 2019b). In
fact, the AI-narratives most closely approximated the SSE mean score for Illicit accounts
(M= 45.90), that is deliberately fabricated stories. But we should note that the SSE scores
for the narratives were clearly associated with their Word Count (r= .55, p= .06) and
Perceived Authenticity (r= .43, p=.14.). Taken altogether, these results suggest that the
cultural depiction of an “average” entity encounter is substandard to the scientific
depiction of an “average” real-life experience.
Hypothesis 4: AI-Narratives Will Reference the Five Recognition Patterns of HP-S
Contextual variables were often present in an apparent attempt to set a suitable
mood and tone for the stories, such as allusions to embedded cues, metaphorical-
symbolic references, or demand characteristics (for a review and discussion, see Houran,
2000). But beyond these literary devices, the raters found generally consistent indications
of the five recognition patterns of HP-S. across the set of narratives. We underscore two
important caveats to this finding. First, no AI-narratives were judged to contain all five
recognition patterns. Second, Table 3 reveals that references to “perceptual contagion”
effects—flurries or clusters of anomalous perceptions—were more tenuous.
Notwithstanding these outcomes, Table 4 does indicate that nearly all the HP-S
recognition patterns were positively and moderately correlated with SSE scores, though
these associations did not reach significance probably because of sample size. That is,
entity encounters of greater perceptual intensity tended to reference more recognition
patterns of HP-S. The only exception was the variable of “dis-ease,” which showed a small
but negative correlation (rs= -.17, p=.56) with SSE scores.
Post-Hoc Analyses
Although not part of our formal hypotheses, a cursory inspection of the AI-
narratives hinted unexpectedly at certain other context effects that researchers of entity
encounters have only recently begun to fully recognize and appreciate. We therefore took
an informal inventory of these references via an iterative discussion between the co-
authors to understand their prevalence. The authors conducted this ancillary exercise
after the masked raters completed the main coding work.
Table 7
Tangential Context Effects in the AI-Narratives
2023, Vol. 3, No. 2, pp. 335-368
PAGE 351
PAGE 352
Journal of Anomalous Experience and Cognition (JAEX)
Environmental Effects
Conceptual and empirical studies suggest that: (a) physical factors in the local
environment (electromagnetic fields, air quality, humidity, infrasound, lighting levels, and
embedded cues; Dagnall et al., 2020), and (b) Gestalt features of the experiential setting
(affordance, immersion, presence, ambiguity, legibility, and memory-associations; Jawer
et al., 2020) can individually or collectively influence the phenomenology of some entity
encounters. Consistent with this idea, 50% of the AI-narratives referenced at least one
pertinent environmental variable.
State of Enchantment
The transpersonal or clinical aftereffects of altered-anomalous experiences is a
burgeoning area of study (Brett et al., 2014; Rabeyron, 2022; Roxburgh & Evenden, 2016).
One frequently reported consequence of entity encounters is a sense of situational-
enchantment (Houran, Lange, & Laythe, 2022). This denotes a complex arousal state
involving absorption within a melee of pleasant ideations and emotions (e. g., excitement,
surprise, awe, and wonder), simultaneously mixed with more unpleasant ideations and
emotions (e. g., uneasiness, disorientation, tension, and unpredictability). This happens
when an individual’s normal waking experience is disrupted by a sudden, unexpected, or
profound awareness that seeds a transformative feeling of connection to a transcendent
agency or ultimate reality (Drinkwater, Massullo, et al., 2022).
Moreover, evidence suggests that enchantment is a mental state that itself
facilitates additional anomalous or exceptional human experiences (Lange & Houran,
2021). It is thus interesting that 42% of the AI-narratives referenced thoughts or feelings
that imply the fictional witnesses experienced some degree of enchantment in response
to their encounters. For the sake of completeness, we should point out that there was
virtually no association (r= -.06, p = .85) between indications of Environmental Variables
and Enchantment. This result might reinforce the interpretation that the depicted
percipients were primarily reacting to the profound nature of their experiences rather
than strictly the environmental cues.
Discussion
Four general conclusions emerge from our exploratory exercise: (a) ChatGPT-3.5
was able to construct archetypal-like entity encounter narratives with a fair level of
believability from information apparently in the mainstream consciousness; (b)
narratives involving different types of entities mapped well to the same unidimensional
and probabilistic hierarchy of S/O anomalies underlying the Survey of Strange Events; (c)
the pattern of item endorsement on the SSE was often consistent across the narratives;
and (d) the contextual details of the different narratives often alluded to one or more of
the five recognition patterns of HP-S, although perceptual contagion was questionable,
and the raters did not agree that all five signs-symptoms were present within any single
narrative. In the spirit of exploration to avoid Type II errors, we purposely did not apply
controls for multiple observations (e. g., setting low alphas, using Bonferroni corrections,
or conducting a split-sample analysis). Yet we are encouraged by the degree to which
our hypotheses were ostensibly affirmed using two-tailed statistical testing of rather
rudimentary data.
This study thus cautiously supports the utility and content validity of the SSE, and
lends some credence to the growing qualitative and quantitative evidence of a core
encounter phenomenon that can be modeled as a biomedical syndrome per the HP-S
framework (Houran et al., 2019b; 2022, 2023Laythe et al., 2021, 2022). Houran et al. (2019
a,b) specifically found evidence that the S/O anomalies reported during such encounters
are predictably structured across experients, albeit this core narrative’s “theme” (Evans,
1987; Houran, 2000; Hufford, 1982) or “meaning” (Drinkwater et al., 2013; Dyne, 2010; Puhle,
2001) alters per the situational or sociocultural context in which the S/O anomalies
2023, Vol. 3, No. 2, pp. 335-368
PAGE 353
PAGE 354
Journal of Anomalous Experience and Cognition (JAEX)
manifest. This suggests that encounter experiences are partly narrative constructions
that are actively shaped by both attitudinal and normative influences (e. g., Childs &
Murray, 2010; Drinkwater et al., 2019; Eaton, 2019; Hill et al., 2018; Ironside & Wooffitt, 2022).
In this sense, our present results and previous research alike (Laythe et al., 2021) clearly
support ChatGPT’s perspective on the ontological reality of the altered-anomalous
experiences that we cited in the Introduction.
Nonetheless, some readers might regard ChatGPT as a controversial tool to
investigate the phenomenology of entity encounters. This criticism certainly has merit, as
unlike the insights or results from well-defined systematic literature reviews or meta-
analyses (Appelbaum et al., 2018), the appropriateness, veracity, or representativeness of
the source material used to generate the AI-accounts is ultimately unclear (e. g., media
reports, novels, films, scientific journals, or a combination of all). A reliance on purely media
(Edwards, 2005), folklore (Goldstein, 2017), or cultural (Waskul & Eaton, 2018) studies are
other ways to gather prototypical narratives, but the corresponding data on S/O events or
the contextual variables associated with them would likely be sensationalized rather than
realistically portrayed (for discussions, see Hill et al., 2018, 2019). Illustratively, Steven
Spielberg’s 1982 blockbuster movie Poltergeist depicted “paranormal portals” and
“possessed trees attacking people”—neither of which correspond to sincerely reported
spontaneous cases. Many authorities likewise caution that professional-grade
informational content must be trustworthy, that is relevant, accurate, current, and credible
(Pattanaphanchai et al., 2013). New research using computerized linguistic analysis might
also help to assess the degree of structural and semantic similarity among the different AI-
narratives, as well as subsequent comparisons with collections of vetted spontaneous
cases. This basic approach has been applied to studies of other anomalous experiences
(e. g., Lange et al., 2015; Martial et al., 2019), so it might be equally fruitful here.
Future research could also address several limitations of the present study. First, we
used single examples derived from ChatGPT-3.5, so it is unclear how well our results
generalize to outputs from the more advanced ChaGBT-4. Second, different ChatGPT
wordings or instructions could skew the narrative content. Houran et al. (2019b) showed
that the micro-phenomenology of encounter narratives can subtly but significantly shift
when percipients’ make reports under different contexts. Third, the types of entity
encounters considered here were representative but certainly not exhaustive. And fourth,
our coding system could have been possibly more controlled or robust. Better approaches
could either be to use raters recruited from outside of anomalistics, or the evaluations of a
cross-disciplinary panel (Bertens et al., 2013). This might help mitigate the lower inter-rater
reliabilities we had with certain macro- and micro- phenomenology variables that seem
to be more complex or nuanced. For all these reasons and more, we deem our approach
and findings as preliminary. At the same time, the present results are merely one piece of
a broader mosaic of ostensibly converging evidence for the interactionist—and perhaps
performative (Drinkwater, Dagnall et al., 2022)—nature of entity encounters.
Moreover, the below-average SSE scores and only fair believability of the AI-
narratives have important implications for future studies. Despite the intense public
interest in the topic and its plethora of associated media, the present findings suggest that
what mainstream consciousness “knows” about “real-life entity encounters” is quite
limited. Specifically, ChatGPT seemingly had little to no access to (or an understanding of)
the spontaneous case reports or survey research in academic literature. Thus, its
composite (archetypal-like) narratives derived from a restricted range of source material
that only represent a cultural understanding of these experiences versus a more rounded,
scientific one. Fraudulent or fabricated accounts should thus be more easily or confidently
identified by informed researchers, as mainstream consciousness has not fully caught up
with the results of scientific studies.
2023, Vol. 3, No. 2, pp. 335-368
PAGE 355
PAGE 356
Journal of Anomalous Experience and Cognition (JAEX)
We certainly hope that our results motivate more thorough investigations. Indeed, AI-
generated narratives offer a new way to study induced “esoteric ideations” or anomalous
experiences, as their private nature makes them difficult to study from a behavioral
perspective. Time will tell whether computer simulations—as routinely used in many
studies of the dynamic behavior of objects or systems in response to conditions that
cannot be easily or safely applied in reality (Winsberg, 2022)—will meaningfully augment
the more traditional methods used to study entity encounters and related experiences,
including surveys (Davis et al., 2020), case studies (Houran & Laythe, 2022), and immersive
experiences like paranormal tourism (Langston & Hubbard, 2019), mirror-gazing exercises
(Caputo et al., 2021), or hypnosis sessions (Connors, 2015). Still, we envision tremendous
opportunities for creative research designs that refine or extend our basic approach. In this
way, we can conceivably explore issues of paranormal belief formation or maintenance, as
well as the content or meaning of entity encounters and other altered-anomalous
experiences from different narrator viewpoints. Some obvious but interesting angles here
include the juxtapositions of skeptic vs believer, solitary vs collective perceptions, indoor vs
outdoor settings, and scenarios involving different forms of belief conversion.
To be sure, research suggests that paranormal entity narratives—as personal
beliefs, shared stories, or putative experiences—can be powerfully engrossing and
shareable experiences due in part to their inherent Versatility, Adaptability, Participatory
Nature, Universality, and Scalability (the VAPUS Model; see Drinkwater et al., 2019; Hill et al.,
2018, 2019; Houran et al., 2020). Daniel and Musgrave (2017) likewise noted that “as people
read, watch, or otherwise consume fictional narratives, they process those stories as if
they were actually witnessing the phenomena those narratives describe, even if those
events may be unlikely or impossible. These synthetic experiences can change beliefs,
reinforce preexisting views, or even displace knowledge gained from other sources for
elites as well as mass audiences” (p. 503). ChatGPT or similar AI-language programs
might therefore generally prove out as innovative tools for what could be characterized
as “locating imagination in popular culture” (Van Es et al., 2021, p. 1). Accordingly, the
social sciences might consider using this new technology for pulse or longitudinal
measurements across a multitude of behavioral phenomena that describe the Zeitgeist,
as well as the many anomalous entities that inhabit it.
References
Appelbaum, M., Cooper, H., Kline, R. B., Mayo-Wilson, E., Nezu, A. M., & Rao, S. M. (2018).
Journal article reporting standards for quantitative research in psychology: The APA
Publications and Communications Board task force report. American Psychologist,
73(1), 3–25. https://doi.org/10.1037/amp0000191
Bertens, L. C. M., Broekhuizen, B. D. L., Naaktgeboren, C. A., Rutten, F. H., Hoes, A. W., van
Mourik, Y., Moons, K. G. M., & Reitsmaet, J. B. (2013). Use of expert panels to define the
reference standard in diagnostic research: A systematic review of published methods
and reporting. PLOS Medicine,10(10), Article e1001531. https://doi.org/10.1371/
journal.pmed.1001531
Bond, T. G., & Fox, C. M. (2015). Applying the Rasch model: Fundamental measurement in
the human sciences (3rd ed). Lawrence Erlbaum.
Brett, C., Heriot-Maitland, C., McGuire, P., & Peters, E. (2014). Predictors of distress
associated with psychotic-like anomalous experiences in clinical and non-clinical
populations. British Journal of Clinical Psychology,53(2), 213–227. https://doi.org/10.1111/
bjc.12036
Caputo, G. B., Lynn, S. J., & Houran, J. (2021). Mirror- and eye gazing: An integrative review
of induced altered and anomalous experiences. Imagination, Cognition, and
Personality,40(4), 418–457. https://doi.org/10.1177/0276236620969632
Childs, C., & Murray, C. D. (2010). “We all had an experience in there together”: A discursive
psychological analysis of collaborative paranormal accounts by paranormal
2023, Vol. 3, No. 2, pp. 335-368
PAGE 357
PAGE 358
Journal of Anomalous Experience and Cognition (JAEX)
investigation team members. Qualitative Research in Psychology,7(1), 21–33. https://
doi.org/10.1080/14780880903304543
Connors M. H. (2015). Hypnosis and belief: A review of hypnotic delusions. Consciousness
and cognition,36, 27–43. https://doi.org/10.1016/j.concog.2015.05.015
Cornell, A. D. (2002). Investigating the paranormal. Helix Press.
Cullum, C., Brierley, G., Perry, G. L. W., & Witkowski, E. T. F. (2017). Landscape archetypes for
ecological classification and mapping. Progress in Physical Geography: Earth and
Environment. 41(1), 95–123. https://doi.org/10.1177/0309133316671103
Dagnall, N., Drinkwater, K., O’Keeffe, C., Ventola, A., Laythe, B., Jawer, M. A., Massullo, B.,
Caputo, G. B., & Houran, J. (2020). Things that go bump in the literature: An
environmental appraisal of “haunted houses.” Frontiers in Psychology, 11, Article 1328.
https://doi.org/10.3389/fpsyg.2020.01328
Daniel, J. F., & Musgrave, P. (2017). Synthetic experiences: How popular culture matters for
images of international relations. International Studies Quarterly,61(3), 503–516. https:/
/doi.org/10.1093/isq/sqx053
Davis, A. K., Clifton, J. M., Weaver, E. G., Hurwitz, E. S., Johnson, M. W., & Griffiths, R. R. (2020).
Survey of entity encounter experiences occasioned by inhaled N,N-
dimethyltryptamine: Phenomenology, interpretation, and enduring effects. Journal of
Psychopharmacology,34(9), 1008–1020. https://doi.org/10.1177/0269881120916143
de Raadt, A., Warrens, M. J., Bosker, R. J., & Kiers, H. A. L. (2021). A comparison of reliability
coefficients for ordinal rating scales. Journal of Classification, 38, 519–543. https://
doi.org/10.1007/s00357-021-09386-5
Drinkwater, K., Dagnall, N., & Bate, L. (2013). Into the unknown: Using interpretative
phenomenological analysis to explore personal accounts of personal paranormal
experiences. Journal of Parapsychology,77(2), 281–294.
Drinkwater, K., Dagnall, N., Houran, J., Denovan, A., & O’Keeffe, C. (2022). Structural
relationships among mental boundaries, childhood imaginary companions, and
anomalous experiences. Psychological Reports. Advanced online publication. https://
doi.org/10.1177/00332941221123235
Drinkwater, K., Laythe, B., Houran, J., Dagnall, N., O’Keeffe, C., & Hill, S. A. (2019). Exploring
gaslighting effects via the VAPUS model for ghost narratives. Australian Journal of
Parapsychology,19(2), 143–179.
Drinkwater, K., Massullo, B., Dagnall, N., Laythe, B., Boone, J., & Houran, J. (2022).
Understanding consumer enchantment via paranormal tourism: Part I - Conceptual
review. Cornell Hospitality Quarterly,63(2), 195–215. https://doi.org/
10.1177/1938965520967920
Dyne, R. (2010). Ghostly experiences: More than imagination, more than just a good story.
Paranthropology,1(1), 27–29.
Eaton, M. (2019). Manifesting spirits: Paranormal investigation and the narrative
development of a haunting. Journal of Contemporary Ethnography 48(2), 155–182.
https://doi.org/10.1177/0891241618756162
Edwards, E. D. (2005). Metaphysical media: The occult experience in popular culture.
Southern Illinois University Press.
Evans, H. (1986). Spontaneous sightings of seemingly autonomous humanoid entities: A
comparative study. Theta,13/14, 10–14.
Evans, H. (1987). Gods, spirits, cosmic guardians: A comparative study of the encounter
experience. Aquarian.
Evans, H. (2001). The ghost experience in a wider context. In J. Houran & R. Lange (Eds.),
Hauntings and poltergeists: Multidisciplinary perspectives (pp. 41–61). Jefferson, NC:
McFarland.
Goldstein, D. E., Grider, S. A., & Thomas, J. B. (2007). Haunting experiences: Ghosts in
contemporary folklore. Utah State University Press. https://doi.org/10.2307/j.ctt4cgmqg
2023, Vol. 3, No. 2, pp. 335-368
PAGE 359
PAGE 360
Journal of Anomalous Experience and Cognition (JAEX)
Guinness, H. (2023, March 21). How does ChatGPT work? Here's the human-written answer
for how ChatGPT works. Zapier: App Tips. https://zapier.com/blog/how-does-chatgpt-
work/ Accessed 24 March 2023.
Hill, S. A., Laythe, B., Dagnall, N., Drinkwater, K., O’Keeffe, C., Ventola, A., & Houran, J. (2019).
“Meme-spirited”: II. Illustrations of the VAPUS model for ghost narratives. Australian
Journal of Parapsychology,19, 5–43.
Hill, S. A., O’Keeffe, C., Laythe, B., Dagnall, N., Drinkwater, K., Ventola, A., & Houran, J. (2018).
“Meme-spirited”: I. A VAPUS model for understanding the prevalence and potency of
ghost narratives. Australian Journal of Parapsychology,18, 117–152.
Houran, J. (2000). Toward a psychology of ‘entity encounter experiences.’ Journal of the
Society for Psychical Research, 64, 141-158.
Houran, J., Hill, S. A., Haynes, E. D., & Bielski, U. A. (2020). Paranormal tourism – Market study
of a novel and interactive approach to space activation and monetization. Cornell
Hospitality Quarterly,61(3), 287–311. https://doi.org/10.1177/1938965520909094
Houran, J., Lange, R., & Laythe, B. (2022). Understanding consumer enchantment via
paranormal tourism: Part II - Preliminary Rasch validation. Cornell Hospitality Quarterly,
63(2), 216–230. https://doi.org/10.1177/1938965520971276
Houran, J., Lange, R., Laythe, B., Dagnall, N., & Drinkwater, K., & O’Keeffe, C. (2019b).
Quantifying the phenomenology of ghostly episodes – Part II: A Rasch model of
spontaneous accounts. Journal of Parapsychology,83(1), 168–192. https://doi.org/
10.30891/jopar.2019.01.03
Houran, J., & Laythe, B. (2022). Case study of recognition patterns in haunted people
syndrome. Frontiers in Psychology,13, Article 879163. https://doi.org/10.3389/
fpsyg.2022.879163
Houran, J., Laythe, B., Lange, R. Dagnall, N., O’Keeffe, C., & Drinkwater, K. (2021). Ghostly
episodes in modern psychometric perspective. Mindfield:Bulletin of the
Parapsychological Association,13(2), 30–40.
Houran, J., Laythe, B., Little, C., & Houran, D. J. (2023). Rethinking a ghostly episode in the
legacy literature. Journal of Anomalistics,23(1), 77-102. http://dx.doi.org/10.23793/
zfa.2023.77
Houran, J., Laythe, B., O’Keeffe, C., Dagnall, N., Drinkwater, K., & Lange, R. (2019a). Quantifying
the phenomenology of ghostly episodes – Part I: Need for a standard
operationalization. Journal of Parapsychology,83(1), 25–46. https://doi.org/10.30891/
jopar.2019.01.03
Houran, J., Little, C., Laythe, B., & Ritson, D. W. (2022). Uncharted features and dynamics of
the South Shields Poltergeist. Journal of the Society for Psychical Research,86(3), 129–
164.
Hufford, D. (1982). The terror that comes in the night: An experience-centered study of
supernatural assault traditions. University of Pennsylvania Press.
Ironside, R. & Wooffitt, R. (2022). Making sense of the paranormal: The interactional
construction of unexplained experiences. Springer Nature. https://doi.org/10.1007/978-
3-030-88407-9
Jaki, S. L. (1999). God and the sun at F·tima. Real View Books.
Jawer, M. A., Massullo, B., Laythe, B., & Houran, J. (2020). Environmental “Gestalt influences”
pertinent to the study of haunted houses. Journal of the Society for Psychical Research,
84(2), 65–92.
Kumar, V. K., & Pekala, R. J. (2001). Relation of hypnosis-related attitudes and behaviors to
paranormal belief and experience: A technical review. In J. Houran & R. Lange (Eds.),
Hauntings and poltergeists: Multidisciplinary perspectives (pp. 260-279). McFarland &
Co.
Lange, R., Greyson, B., & Houran, J. (2015). Using computational linguistics to understand
near-death experiences: Concurrent validity for the NDE Scale. Psychology of
Consciousness: Theory, Research, and Practice,2(1), 79–89. https://doi.org/10.1037/
cns0000040
2023, Vol. 3, No. 2, pp. 335-368
PAGE 361
PAGE 362
Journal of Anomalous Experience and Cognition (JAEX)
Lange, R., & Houran, J. (1996). Role of contextual mediation in direct versus reconstructed
angelic encounters. Perceptual and Motor Skills,83, 1259–1270.
Lange, R., & Houran, J. (2021). Replicable survey evidence for an ‘enchantment–psi’ loop.
Journal of Transpersonal Psychology,53(2), 140–156.
Lange, R., Houran, J., Sheridan, L., Dagnall, N., Drinkwater, K., O’Keeffe, C., & Laythe, B. (2020).
Haunted people syndrome revisited: Conceptual parallels between subjective
paranormal episodes and putative accounts of group-stalking. Mental Health,
Religion, & Culture,23(7), 532–549. https://doi.org/10.1080/13674676.2020.1767552
Lange, R., Irwin, H. J., & Houran, J. (2000). Top-down purification of Tobacyk’s Revised
Paranormal Belief Scale. Personality and Individual Differences,29(1), 131–156. https://
doi.org/10.1016/S0191-8869(99)00183-X
Lange, R., Thalbourne, M. A., Houran, J., & Storm, L. (2000). The Revised Transliminality Scale:
Reliability and validity data from a Rasch top-down purification procedure.
Consciousness and Cognition,9(4), 591–617. https://doi.org/10.1006/ccog.2000.0472
Langston, W., & Hubbard, T. (2019). Shadow walking: Will a ghost walk tour affect belief in
ghosts? Journal of Parapsychology, 83(1), 47–68. http://doi.org/10.30891/
jopar.2019.01.04
Laythe, B., Houran, J., Dagnall, N., & Drinkwater, K. (2021). Conceptual and clinical
implications of a “haunted people syndrome.” Spirituality in Clinical Practice,8(3), 195–
214. https://doi.org/10.1037/scp0000251
Laythe, B., Houran, J., Dagnall, N., Drinkwater, K., & O’Keeffe, C. (2022). Ghosted! Exploring the
haunting reality of paranormal encounters. McFarland & Co.
Laythe, B., Houran, J., & Ventola, A. (2018). A split-sample psychometric study of haunters.
Journal of the Society for Psychical Research,82(4), 193–218.
Lifshitz, M., van Elk, M., & Luhrmann, T. M. (2019). Absorption and spiritual experience: A
review of evidence and potential mechanisms. Consciousness and Cognition,73,
Article 102760. https://doi.org/10.1016/j.concog.2019.05.008
Little, C., Laythe, B., & Houran, J. (2021). Quali-quantitative comparison of childhood
imaginary companions and ghostly episodes. Journal of the Society for Psychical
Research,85(1), 1–30.
Mack, J. E. (1994). Abduction: Human encounters with aliens. Scribner.
Maher, M. C. (1999). Riding the waves in search of the particles: A modern study of ghosts
and apparitions. Journal of Parapsychology,63(1), 47–80.
Martial, C., Cassol, H., Charland-Verville, V., Pallavicini, C., Sanz, C., Zamberlan, F., Vivot, R. M.,
Erowid, F., Erowid, E., Laureys, S., Greyson, B., & Tagliazucchi, E. (2019). Neurochemical
models of near-death experiences: A large-scale study based on the semantic
similarity of written reports. Consciousness and Cognition,69, 52–69. https://doi.org/
10.1016/j.concog.2019.01.011
McHarg, J. F. (1973). Poltergeist and apparitional haunting phenomena affecting the
family and associates of an adolescent girl with well-controlled epilepsy. In W. G. Roll,
R. L. Morris & J. D. Morris (Eds.), Research in parapsychology 1972 (pp. 17–19). Scarecrow
Press.
O'Neill T. A. (2017). An overview of interrater agreement on Likert scales for researchers and
practitioners. Frontiers in Psychology,8, Article 777. https://doi.org/10.3389/
fpsyg.2017.00777
Parker, A. (2021). Thought-forms gone rogue: A theory for psi-critics and
parapsychologists. Journal of Scientific Exploration,35(1), 95–132. https://doi.org/
10.31275/20211901
Pattanaphanchai, J., O'Hara, K., & Hall, W. (2013). Trustworthiness criteria for supporting
users to assess the credibility of web information. WWW '13 Companion: Proceedings
of the 22nd International Conference on World Wide Web, May, 1123–1130. https://
doi.org/10.1145/2487788.2488132
2023, Vol. 3, No. 2, pp. 335-368
PAGE 363
PAGE 364
Journal of Anomalous Experience and Cognition (JAEX)
Perrotta, G. (2019). The phenomenon of demonic possession: Definition, contexts and
multidisciplinary approaches. Journal of Psychology and Mental Health Care,3(2), 1-13.
https://doi.org/10.31579/2637-8892/019
Petitmengin, C., Remillieux, A., & Valenzuela-Moguillansky, C. (2019). Discovering the
structures of lived experience: Towards a micro-phenomenological analysis method.
Phenomenology and the Cognitive Sciences,18, 691-730. https://doi.org/10.1007/
s11097-018-9597-4
Puhle, A. (2001). Learning from historical cases: Six selected poltergeist cases from the
1700s in Germany. European Journal of Parapsychology,16, 61-72.
Rabeyron, T. (2022). When the truth is out there: Counseling people who report anomalous
experiences. Frontiers in Psychology,12, Article 693707. https://doi.org/10.3389/
fpsyg.2021.693707
Randles. J. (1997). The truth behind Men in Black: Government agents—or visitors from
beyond. St. Martin’s Press.
Rasch, G. (1980). Probabilistic models for some intelligence and attainment tests
(Copenhagen, Danish Institute for Educational Research), expanded edition (1980)
with foreword and afterword by B. D. Wright. University of Chicago Press. (Original work
published in 1960).
Roll, W. G. (1977). Poltergeists. In B. B. Wolman (Ed.), Handbook of parapsychology (pp.
382–413). Van Nostrand Reinhold.
Ross, C. A., & Joshi, S. (1992). Paranormal experiences in the general population. Journal of
Nervous and Mental Disease,180(6), 357–361. https://doi.org/
10.1097/00005053-199206000-00004
Roxburgh, E. C., & Evenden, R. E. (2016). ‘They daren’t tell people’: Therapists’ experiences of
working with clients who report anomalous experiences. European Journal of
Psychotherapy & Counselling, 18(2), 123–141. https://doi.org/
10.1080/13642537.2016.1170059
Seamon, D. (2000). A way of seeing people and place: Phenomenology in environment-
behavior research. In S. Wapner, J. Demick, T. Yamamoto, & H. Minami (Eds.),
Theoretical perspectives in environment-behavior research: Underlying assumptions,
research problems, and methodologies (pp. 157–178). Kluwer Academic Publishers.
Sheridan, L., James, D. V., & Roth, J. (2020). The phenomenology of group stalking (‘gang-
stalking’): A content analysis of subjective experiences. International Journal of
Environmental Research and Public Health,17(7), Article 2506. https://doi.org/10.3390/
ijerph17072506
Tobacyk, J. J. (1988). A Revised Paranormal Belief Scale. Unpublished manuscript,
Louisiana Tech University, Ruston, LA
Tobacyk, J. (2004). The Revised Paranormal Belief Scale. International Journal of
Transpersonal Studies,23(1), 94–98. https://doi.org/10.24972/ijts.2004.23.1.94
van Es, N., Reijnders, S., Bolderman, L., & Waysdorf, A. (Eds.) (2021). Locating imagination in
popular culture: Place, tourism and belonging. Routledge.
Waskul, D., & Eaton, M. (Eds.) (2018). The supernatural in society, culture, and history.
Templeton University Press.
Winsberg, E. (2022, Winter ed.). Computer simulations in science. In E. N. Zalta & U.
Nodelman (Eds.), The Stanford encyclopedia of philosophy. https://plato.stanford.edu/
archives/win2022/entries/simulations-science/
Young, S. (2018). Children who see fairies. Journal for the Study of Religious Experience,
4(1), 81–98.
2023, Vol. 3, No. 2, pp. 335-368
PAGE 365
PAGE 366
Journal of Anomalous Experience and Cognition (JAEX)
Appendix A
Sample ChatGPT Narrative of an Entity Encounter (generated 01 March 2023)
Write a convincing account of a real-life haunted house
The house had always had a reputation for being haunted. It had stood on the same spot for over
a century, and during that time, many strange things had been reported to happen within its walls.
People had reported hearing footsteps in the middle of the night, doors would slam shut on their
own, and objects would move without explanation. Some even claimed to have seen ghostly
apparitions wandering through the rooms.
One family moved into the house, hoping that the stories were just exaggerated rumors. But as soon
as they stepped inside, they felt a chilling presence. The air was cold and heavy, and the hairs on
the back of their necks stood on end.
As they began to unpack their belongings, strange things started to happen. Doors would open and
close on their own, and they could hear whispering voices that seemed to be coming from nowhere.
One night, the family woke up to find all of their furniture had been moved around while they slept.
Chairs and tables had been stacked on top of each other, and some had even been turned upside
down.
The family tried to ignore the strange occurrences, but they couldn't shake the feeling that they
were being watched. They decided to call in paranormal investigators, who set up cameras and
recorders throughout the house.
The footage they captured was shocking. Doors would open and close on their own, and objects
would move without explanation. In one instance, a chair moved across the room, as if by an
invisible force.
The investigators concluded that the house was indeed haunted, and that the family was living with
a malevolent spirit. They advised the family to leave the house, as it was not safe for them to stay.
The family took their advice and moved out of the house, but the experience had left a lasting
impression on them. They never forgot the eerie feeling of being watched, or the terrifying
paranormal activity that had taken over their home.
To this day, the house remains empty, its windows boarded up, and its doors locked tight. The locals
still talk about the haunted house, warning visitors to stay away from its ghostly inhabitants.
Appendix B
Sample ChatGPT Control Narrative (generated 01 March 2023)
Write a convincing account of someone seeing the aurora borealis for the first time
Sarah had always dreamed of seeing the Aurora Borealis, also known as the Northern Lights. She
had heard stories of its beauty and magnificence from her friends who had witnessed it before. She
planned a trip to Norway during the winter months to witness the natural wonder for herself.
As she stood outside, bundled up in her warmest clothing, she looked up at the sky in anticipation.
Suddenly, a greenish glow appeared on the horizon, slowly growing and expanding across the sky.
The colors shifted and danced, with hues of green, purple, and pink blending together in a
mesmerizing display.
Sarah was spellbound. She had never seen anything like it before. The colors swirled and changed,
creating a sense of movement and energy that seemed alive. The Northern Lights seemed to take
on a life of their own, as if they were communicating with her in a language she could not quite
understand.
As she watched, the colors intensified and brightened, casting a soft glow over the snowy
landscape around her. It was as if she was standing in the middle of a dream world, a place of
magic and wonder that she never knew existed.
For Sarah, the experience was truly unforgettable. She felt a deep sense of awe and wonder, and
was overwhelmed by the beauty of the Northern Lights. She knew that this moment would stay with
her forever, a memory that she would cherish for the rest of her life.
Witnessing the Aurora Borealis for the first time is a truly magical experience that leaves a lasting
impression on those who are lucky enough to see it. The colors, movement, and energy of the
Northern Lights create a sense of wonder and awe that is unlike anything else in the world.
2023, Vol. 3, No. 2, pp. 335-368
PAGE 367
PAGE 368
Journal of Anomalous Experience and Cognition (JAEX)
Phänomenologie von KI-generierten "Entity Encounter"-Narrativen
James Houran Brian Laythe
Zusammenfassung: Zielsetzung: Wir haben das auf künstlicher Intelligenz (KI) basierende
Sprachprogramm ChatGPT-3.5 verwendet, um zwölf Typen von Erzählungen über mystische,
übernatürliche oder anderweitig anomale Begegnungen mit Wesenheiten zu vergleichen, die aus
dem öffentlich zugänglichen Informationskorpus konstruiert wurden, und ihre Details mit der
Phänomenologie spontaner Erzählungen mittels der Survey of Strange Events (SSE) und der
Grounded Theory (gegenstandsbezogene Theoriebildung) des Haunted People Syndrome (HP-S)
verglichen. Methoden: Eine strukturierte Inhaltsanalyse durch zwei unabhängige und blinde
Beurteiler untersuchte, ob die zusammengesetzten KI-Erzählungen: (a) jeden Begegnungstyp
abdecken, (b) der Rasch-Hierarchie der anomalen Wahrnehmungen der SSE entsprechen, (c)
einen durchschnittlichen SSE-Score aufweisen und (d) auf die fünf Erkennungsmuster des HP-AbsS
verweisen. Ergebnisse: Wir fanden mäßige Hinweise auf ein zentrales Begegnungsphänomen, das
den KI-Erzählungen zugrunde liegt. Jeder Begegnungstyp wurde durch eine KI-generierte
Beschreibung repräsentiert, die sich leicht auf die SSE abbilden ließ, wenngleich ihre Inhalte nur eine
geringe Glaubwürdigkeit und geringe, aber im Allgemeinen positive Korrelationen untereinander
aufwiesen. Die Erzählungen entsprachen auch unterdurchschnittlichen SSE-Werten und bezogen
sich auf mindestens ein HP-S Erkennungsmuster. Schlussfolgerungen: Prototypische Darstellungen
von Erfahrungen mit Entitätsbegegnungen, die auf populärem Quellenmaterial beruhen, kommen
der Phänomenologie ihrer realen Gegenstücke sicherlich nahe, stimmen aber nicht vollständig mit
ihnen überein. Wir erörtern die Auswirkungen dieser Ergebnisse auf zukünftige Studien.
Translation: Eberhard Bauer
Fenomenologia das Narrativas de "Encontros com Entidades" Geradas por IA
James Houran Brian Laythe
Resumo: Objetivo: Utilizamos o programa de linguagem baseado em inteligência artificial (IA)
ChatGPT-3.5 para comparar doze tipos de narrativas de encontros com entidades místicas,
sobrenaturais ou anômalas, construídas a partir de material no corpus de informações
publicamente disponível, e comparamos seus detalhes com a fenomenologia de relatos
espontâneos por meio da Survey of Strange Events (SSE) e da teoria fundamentada da Haunted
People Syndrome (HP-S). Métodos: A análise de conteúdo estruturada por dois avaliadores
independentes e ocultos explorou se as narrativas geradas por IA: (a) abrangeriam cada tipo de
encontro, (b) mapeariam a hierarquia Rasch de percepções anômalas da SSE, (c) mostrariam
uma pontuação média da SSE e (d) fariam referência aos cinco padrões de reconhecimento da
HP-AbsS. Resultados: Encontramos evidências moderadas de um fenômeno de encontro central
subjacente às narrativas da IA. Cada tipo de encontro foi representado por uma descrição gerada
por IA que foi prontamente mapeada para o SSE, embora seu conteúdo tenha mostrado apenas
uma credibilidade razoável e baixas, embora em maioria positivas, correlações entre si. As
narrativas também correspondiam a pontuações de SSE abaixo da média e faziam referência a
pelo menos um padrão de reconhecimento HP-S. Conclusões: As descrições prototípicas de
experiências de encontro com entidades baseadas em material de origem pública certamente se
aproximam, mas não correspondem totalmente, à fenomenologia de suas contrapartes na vida
real. Discutimos as implicações desses resultados para estudos futuros.
Portuguese translation: Antônio Lima
Fenomenología de Narrativas de “Encuentros con una Entidad”
Generadas por Inteligencia Artificial (IA)
James Houran Brian Laythe
Resumen: Objetivo: Usamos el programa de lenguaje basado en inteligencia artificial (IA)
ChatGPT-3.5 para comparar 12 tipos de narraciones de encuentros con entidades místicas,
sobrenaturales, o anómalas construidas a partir de material del corpus de información disponible
públicamente, y comparamos sus detalles con la fenomenología de los relatos espontáneos a
través de la Encuesta de Sucesos Extraños (SSE) y la teoría fundamentada del Síndrome de la
Gente Embrujada (HP-S). Método: El análisis de contenido estructurado realizado por dos
evaluadores independientes y enmascarados exploró si las narraciones creadas por IA: (a)
cubrían todo tipo de encuentro, (b) correspondían con la jerarquía Rasch de percepciones
anómalas del SSE, (c) mostraban una puntuación media del SSE, y (d) hacían referencia a los cinco
patrones de reconocimiento del HP-AbsS. Resultados Encontramos evidencia moderada de un
fenómeno de encuentro central subyacente a las narraciones de la IA. Cada tipo de encuentro
estaba representado por una descripción generada por la IA que correspondía claramente con el
SSE, aunque sus contenidos mostraban sólo una credibilidad aceptable y correlaciones bajas pero
generalmente positivas entre sí. Las narraciones también correspondían a puntuaciones de SSE
por debajo de la media y hacían referencia al menos a un patrón de reconocimiento HP-S.
Conclusión: Las descripciones prototípicas de experiencias de encuentros con entidades basadas
en material de fuentes populares ciertamente se aproximan, aunque no coinciden plenamente, a
la fenomenología de sus contrapartes de la vida real. Discutimos las implicaciones de estos
resultados.
Spanish translation: Etzel Cardeña
2023, Vol. 3, No. 2, pp. 335-368
