Page 1 of 12
Transactions on Machine Learning and Artificial Intelligence - Vol. 9, No. 6
Publication Date: December 25, 2021
DOI:10.14738/tmlai.96.11290. Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood
Type. Transactions on Machine Learning and Artificial Intelligence, 9(6). 26-37.
Services for Science and Education – United Kingdom
AI-based Analysis on Relationship between Genes and
Personality: Evaluation Results with the ABO Blood Type
Masayuki Kanazawa
Human Sciences ABO Center, Tokyo, Japan
ABSTRACT
AI can be applied in various ways to the measurement of personality in psychology.
Measuring the impact of a single gene on personality can be handled by AI
technologies, at least technically, i.e., using supervised learning models of machine
learning. The ABO blood type is a relatively easy biological marker to examine;
therefore, people in many countries know their type, and its impact on the
relationship with personality has been the subject of a large amount of research. In
this study, we selected the ABO blood type as the target gene, examined its
association with personality, and cross-checked the results with previous works.
Two scales were used to measure personality: a) blood type personality traits
extracted from previous studies, and b) the TIPI-J, a simplified version of the Big
Five personality test. In the former, the AI was able to predict the respondents’
blood types with a higher probability than chance, while in the latter, the accuracy
was within the range of chance. These obtained results were also discussed.
Keywords: ABO; Blood Type; Gene; Big Five; Personality.
INTRODUCTION
Aims of This Study
The use of artificial intelligence (AI) for personality measurement has a variety of possible
applications in psychology. Many of them are conceptual, but some studies have yielded
concrete results [1-2].
One possible application of AI is to investigate the relationship between genes and personality.
In general, traditional studies examined the similarity of twins' personalities [3], or the
relationship between personality tests and genes [4]. However, no clear consensus has been
reached on the relationship between a single gene and personality so far. The most typical
method for these studies is ANOVA, and traditional ANOVA can only handle linear relationships,
not non-linear ones. Meanwhile, these issues are typical examples of supervised learning in AI,
and since the models are relatively simple, they can be tested on currently available “ready- made” platforms, i.e., AWS or Microsoft Azure, at least technically. The aim of this study is to
provide a practical and pioneering application of using AI to check these non-linear
relationships.
Naturally, the most important issue is which gene to select. To examine multiple genes, DNA
testing is necessary, but this can be time-consuming and expensive. Since blood type is a
biological marker that is relatively easy to test, many people in many countries, especially in
East Asian countries like Japan, know their own ABO blood type. More than 90% of Japanese
Page 2 of 12
27
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
people know their types, and a lot of research has been conducted on its relationship with
personality, not only in Japan but all over the world. As mentioned above, DNA testing is
necessary to accurately determine genes, which requires considerable time and cost. However,
in the case of the ABO blood type, self-reporting is not a problem as long as the sample is
Japanese, making it suitable for a pioneering study like this one. Furthermore, it is easy to
compare and cross-check the results with those of many previous studies. Therefore, in this
study, we selected ABO blood type as the target gene, examined its association with personality,
and compared it with studies that are representative of the previous research in this field.
Big Five Personality Test
The “Big Five” personality test is the most commonly used personality test in current
psychology. As the name suggests, the Big Five test is a comprehensive description of
personality by five factors called the Big Five [5-6]. These five factors are usually referred to as
Neuroticism, Extraversion, Openness, Agreeableness, and Conscientiousness. In this model,
question items are collected from dictionaries and traditional personality tests. Personality
scales are re-analyzed, and the five factors are extracted through factor analysis. In this way,
the Big Five are characterized by a bottom-up process without assuming any background
theory, and personality is comprehensively captured by the five factors [7].
As mentioned earlier, the Big Five is a questionnaire-based personality assessment that
consists of answering a series of questions about multiple self-reported personality traits.
These traits are then integrated into five personality factors through statistical processing.
Theoretically, the self-reported answers will appear directly or indirectly in the results.
Recently, a variety of efforts have been made to measure psychological factors with a small
number of question items. Typical examples are subjective well-being [8] and self-esteem [9],
which have been used in many studies. In 2003, for the Big Five personality tests, Gosling,
Rentfrow and Swann developed a 10-item inventory with a seven-point scale, the Ten-Item
Personality Inventory (TIPI) [10]. A Japanese version of this personality test was developed by
Oshio, Abe and Cutrone in 2012 [11]. The test-retest reliabilities of these were 0.62-0.77 and
0.64-0.84, and Cronbach's alphas were 0.40-0.73 and 0.72-0.91 [10-11], which largely
supported the validity of these two tests.
Blood Type Personality Theory
In 1927, Furukawa, a Japanese educational psychologist, published the world’s first academic
study of blood type and personality based on statistics [12-13]. Later, Nomi, an independent
Japanese researcher, further developed Furukawa’s study and published his work in 1971 [14],
which has had the greatest impact on current research [15-16]. Nomi utilized various methods,
including questionnaires, observations and statistical analyses of human behaviors, and
surveys of the distribution of blood types among various occupations and special groups (Table
1). He claimed that the sample size of his studies was tens of thousands in total.
In Japan, South Korea, and Taiwan, half or more of the population believed in the relationship
between blood type and personality [15, 17-20].
Sato, Miyazaki, and Watanabe, a group of Japanese psychologists, conducted a free-response
survey of 197 college students [21]. Another Japanese group, led by Sakamoto and Yamazaki,
Page 3 of 12
28
Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021
Services for Science and Education – United Kingdom
has surveyed 177 college students on 24 personality traits in annual opinion polls conducted
by company affiliated with one of Japan's major television stations [22]. These results are
shown in Table 2, and in general, these personality traits studied by Japanese academic
researchers matched with those studied by Nomi (Table 1).
Table 1. Blood Type, Personality, and High Distribution Rate
Blood
Type
Personality High Distribution Rate
A Have a sense of duty for “someone.” Suppress
emotions and desires. Value gentle compassion and
perceptions. Observe rules, custom and order;
avoid extremes. On the other hand, a bit
conventional. Very consistent, drawing a clear line.
Most stubborn and short-tempered inside.
Education minister
High-ranking sumo
wrestler
B Self-paced behavior. Reluctant to be argued with or
restrained. Cognitively flexible, highly innovative
and accepting of new people. Least influenced by
their surroundings, unconcerned; most careless. In
general, not particular about things.
Baseball hitter
O Strong desire to live and full of vitality. Strongly
purpose-oriented. Once target is set, go straight
ahead without hesitation. Physical intimacy for
friends, family-oriented. Naked openness and
parental love for best friends. On the other hand,
very wary of “outsiders” or the unknown.
Prime minister
Foreign minister
Baseball hitter
AB Rational, businesslike. Duality with a calm, cool
stable side and an easily disturbed side with
sentimental fragility. Very friendly and tidy; treat
others with kindness when asked; smiling. Keep a
certain distance from others.
Foreign minister
Education minister
Many academic studies have used multi-item personality tests, i.e., the Big Five test, but the
results have been considered as inconsistent [23-35]. Thus, there remains an endless academic
controversy on whether the relationship has been scientifically confirmed or not. Furthermore,
there was little statistical difference among respondents who knew little about blood type
personality traits [36]. A 2014 study re-analyzed data from 10,000 respondents to a survey on
consumer life in Japan and the United States, but no meaningful differences were found [37].
Page 4 of 12
29
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
Table 2. Blood Type and Its Associated Stereotypes (#1: [21]; #2: [22])
Blood
Type
# Personality
A 1 Meticulous, Nervous, Serious
2 I am careful when doing something.
I am serious when I should be so.
I am often worried about things.
I make an effort toward my goal.
B 1 Self-paced, Individual, Lukewarm, Egoistic, Self-centered, Optimistic,
Pleasant
2 I often change my mind.
I am not particular about things.
I cannot be quiet and I make merry when I am delighted.
I am ready to keep company with everyone.
O 1 Big-hearted, Laid back, Unassuming
2 I have a lot of friends.
I am ready to keep company with everyone.
I cannot be quiet and I make merry when I am delighted.
I am not particular about things.
AB 1 Dual personality, Two-faced, Oddball, Hard to understand
2 I do not change my idea after I present it.
I make an effort toward my goal.
I sometimes burst into a rage.
I often change my mind.
Contemporary Trends and Issues
Self-fulfilling prophecy is a phenomenon in which a person who believes in a certain prophecy
begins to behave accordingly, and thereby the prophecy becomes reality. Psychologists have
examined a classic example: astrology [38-39]. As stated above, half or more of the people in
Japan, South Korea, and Taiwan believe in the relationship between blood type and personality
[15, 17-20]. Therefore, the self-fulfilling knowledge of astrology suggests that a person's
personality would changes in the direction of personality traits associated with their blood
type, at least theoretically.
Based on this hypothesis of self-fulfilling prophecy, several large-scale Japanese academic
surveys clearly validated the phenomenon. Archetypical sample sizes for these were several
thousands or more [40-42]. However, respondents without knowledge of astrology or blood
type traits, showed no consistent statistical differences [40]. Therefore, the current scientific
consensus is that these differences are caused by “contamination by knowledge,” or self- fulfilling prophecy [15, 17-18, 21-22, 36, 38-39, ,41-42].
Some studies have focused on biological factors: in 2015, a Japanese study using DNA testing
methods and the Temperament and Character Inventory (TCI) personality test, which assumes
the influence of neurotransmitters, found that among 1,427 participants, those with blood type
A tended to be “persistent,”, as predicted [43]. Another researcher in the United States assessed
both the ABO phenotype and its genotype and investigated the association of disequilibrium
between the ABO genes and the DBH genes [44-45].
Page 5 of 12
30
Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021
Services for Science and Education – United Kingdom
Personality is influenced by genetic factors, i.e., gender or age, and these interactions are
considered as non-linear [46-49]. However, the majority of previous studies have assumed that
the effect of blood type was linear, regardless of the nature of these factors [12-13, 15-19, 21-
37]. Statistical methods used in the design of questionnaire-based personality tests, i.e.,
correlation or factor analysis, basically assume a linear relationship between variables.
Therefore, there is no theoretical guarantee that traditional personality tests based on these
statistical methods could properly handle real non-linear data.
PARTICIPANTS AND METHODS
Participants
The data for the survey was collected through an Internet research company, using the method
of crowdsourcing. The survey was conducted in 2021 with a sample of 3,000 Japanese
respondents between the ages of 20 and 59. The participants were asked to rate a total of eight
items corresponding to four blood types (A, B, O, AB), using a score from one to five to indicate
how closely each item matched their own personality traits (the larger the number, the more
fitting the trait). The participants were also asked to indicate which blood type they thought
these eight items corresponded to. In addition, we provided them with a score from one to three
indicating the strength of the relationship (the higher the number, the stronger the
relationship) and a score from one to four indicating their knowledge of blood type personality
theory (the higher the number, the more knowledgeable they were).
In line with the methods of the aforementioned psychological personality tests, we deliberately
selected the traits that would certainly make a difference, i.e., the common stereotype of the
traits consistent with prior academic studies, showing a large difference and a mean value close
to 50%, not showing extreme values, and being consistent with prior research in other studies.
The results are as follows:
Type A: Meticulous, nervous
Type B: Self-paced, self-centered
Type O: Big-hearted, laid-back
Type AB: Easily misunderstood, dual personality
A simplified Big Five personality test, the Ten-Item Personality Inventory (TIPI) [10], Japanese
version (TIPI-J) [11], was also conducted simultaneously with these same participants.
Since this study was not a medical study involving human subjects, the research ethics review
committee determined that there were no ethical issues with using only information that was
already unlinked and anonymized.
The questions regarding blood type traits for this study were extracted from the reviewed
scientific papers (Table 2). These items were again checked by a crowdsourcing company that
had passed the Japanese privacy review (JIS Q 15001) mentioned earlier. The company
confirmed that there were no problems with the questionnaire items. The company provides
anonymized data to its clients and obtains informed consent from respondents prior to its
surveys. In this survey, the blood type of the participants was determined by self-reporting, as
most Japanese people know their own blood type; it was common practice in Japan until
recently to test the blood type of newborns. As the result, only 166 out of 3,000 respondents
(5.5% of the total) did not know their own blood type, so we used data from the remaining
Page 6 of 12
31
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
2,834 individuals whose blood types were known. All samples were evenly distributed by age
and gender in 10-year increments (Appendix). The distributions of participants’ blood types
were almost equal to the Japanese average [50].
ANALYTICAL METHODS
First, we tested whether AI predicts participants' blood types more than chance. Second, to
focus on whether the self-fulfilling prophecy phenomenon was occurring, we conducted an
analysis using data from participants who either “do not know their blood type traits” or “do
not believe in the relationship” (hereafter referred to as the “no knowledge” group).
The analysis methods for personality are as follows:
Analysis 1: Blood type prediction using AI with blood type traits
Analysis 2: Blood type prediction using AI with TIPI-J
Analysis 3: ANOVA for blood type and its traits for all participants
Analysis 4: ANOVA for blood type and its traits for the "no knowledge" group
Analysis 5: ANOVA for blood type and TIPI-J for all participants
All the data was stored in Microsoft Azure, and Microsoft Azure Machine Learning Studio was
used for predictions. The algorithms we used were Multiclass Logistic Regression, Multiclass
Neural Network, Multiclass Decision Jungle, and Multiclass Decision Forest. Predictions were
run four times each (random seeds from one to four), and the average values were used as the
accuracy rates.
We conducted an analysis of variance (ANOVA) using self-reported ABO phenotypes (O, A, B,
AB) with personality trait scores as the dependent variable. The alpha ratio was set at 0.05.
Prior to the ANOVA analysis, the normality of the distribution was checked for each personality
trait score, and it was normally distributed. The data were analyzed using jamovi software
version 1.2.27. The effect sizes [51] were also calculated.
RESULTS
Analysis 1: Blood Type Predictions with Blood Type Trait
The results for the Multiclass Logistic Regression, Multiclass Neural Network, Multiclass
Decision Jungle, and Multiclass Decision Forest algorithms showed accuracies of 0.434, 0.418,
0.395, and 0.356, respectively (Chart 1).
Chart 1. Accuracy of Blood Type Predictions with Blood Type Traits
0.434
0.418
0.395
0.356
0.384
0.34 0.36 0.38 0.40 0.42 0.44 0.46
Multiclass Logisitic Regression
Multiclass Neural Network
Multiclass Decision Jungle
Multiclass Decision Forest
Chance (Type A)
Page 7 of 12
32
Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021
Services for Science and Education – United Kingdom
Analysis 2: Blood type prediction using AI with TIPI-J
The results for Multiclass Logistic Regression, Multiclass Neural Network, Multiclass Decision
Jungle, and Multiclass Decision Forest algorithms showed accuracies of 0.376, 0.375, 0.344, and
0.323, respectively (Chart 2).
Chart 2. Accuracy of Blood Type Predictions with TIPI-J
As mentioned above, type A is the most common blood type among Japanese people, accounting
for 0.384 (1,089 persons) of the total number of participants in this study. Therefore, if AI
simply predicted each participant to be type A, the accuracy would have been 0.384. Microsoft
Azure Machine Learning Studio predicted the blood type with a lower accuracy than this value
in all cases.
Analysis 3: ANOVA for Blood Type and Its Traits for All Participants
In the survey’s ANOVA result (Table 3), all four types showed the same results as those shown
for blood type traits in the preceding psychology papers (Table 2). The score for each blood
type was the sum of the two question items that corresponded to that blood type. All types were
statistically significant at p < 0.05, and after the Bonferroni’s correction. The magnitude of the
difference: η2 = 0.035 at the maximum, thus all the effect sizes were small. All of the responses
were consistent with the most common stereotypes of blood types that respondents expected.
Table 3. Result of ANOVA for Traits Scores and Blood Type
Blood Type
Traits
Average Scores by Blood Type
F η2 p
A
(N =
1,089)
B
(N = 616)
O
(N = 844)
AB
(N = 285)
A 6.73 5.98 6.05 6.31 34.10 0.035 <0.001 *
B 6.35 6.92 6.46 6.43 16.52 0.017 <0.001 *
O 6.17 6.36 6.88 6.15 34.68 0.035 <0.001 *
AB 5.55 5.55 5.51 6.51 30.08 0.031 <0.001 *
Note. Highest scores that match with blood type traits, and p < 0.05 are highlighted in bold. * p <
0.05 after the Bonferroni’s correction
On the question item “Do you think blood type and personality are related?”, 8.2% of the
respondents answered “related,” 51.7% answered “somewhat related,” 26.3% answered “not
related,” and 13.8% answered “I don't know.” On the question item “Do you know the traits and
0.376
0.375
0.344
0.323
0.384
0.28 0.30 0.32 0.34 0.36 0.38 0.40
Multiclass Logisitic Regression
Multiclass Neural Network
Multiclass Decision Jungle
Multiclass Decision Forest
Chance (Type A)
Page 8 of 12
33
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
compatibilities of blood types?”, 4.0% answered “I know a lot,” 37.8% answered “I know some,”
40.5% answered “I know a little,” and 17.7% answered “I don't know at all.”
Analysis 4: ANOVA for Blood Type and Its Traits of the "No Knowledge" Group
In the survey’s ANOVA result (Table 4), all four types showed the same results as those shown
for blood type traits in the preceding psychology papers (Table 2). The score for each blood
type was the sum of the two question items that corresponded to that blood type. Three types
were statistically significant at p < 0.05, and after the Bonferroni’s correction. The magnitude
of the difference: η2 = 0.039 at the maximum, thus all the effect sizes were small.
Table 4. Result of ANOVA for Traits Scores and Blood Type
Blood Type
Traits
Average Scores by Blood Type
A F η2 p
(N = 207)
B
(N = 152)
O
(N = 182)
AB
(N = 54)
A 6.73 5.98 6.05 6.31 A 6.73 5.98
B 6.35 6.92 6.46 6.43 B 6.35 6.92
O 6.17 6.36 6.88 6.15 O 6.17 6.36
AB 5.55 5.55 5.51 6.51 AB 5.55 5.55
Note. Highest scores that match with blood type traits, and p < 0.05 are highlighted in bold. * p <
0.05 after the Bonferroni’s correction
Analysis 5: ANOVA for TIPI-J by Blood Type
In the survey’s ANOVA result (Table 5), two factors were statistically significant at p < 0.05, and
one after the Bonferroni’s correction. The magnitude of the difference: η2 = 0.005 at the
maximum, thus all the effect sizes were considerably small.
Table 5. Result of ANOVA for Traits Scores and Blood Type
Factors
Average Scores by Blood Type
F η2 p
A
(N =
1,089)
B
(N = 616)
O
(N = 844)
AB
(N = 285)
Extraversion 3.71 3.78 3.74 3.78 0.52 0.001 0.669
Agreeableness 4.72 4.64 4.71 4.65 0.88 0.001 0.451
Conscientiousness 3.69 3.55 3.52 3.56 2.98 0.003 0.030
Neuroticisms 4.33 4.26 4.29 4.31 0.54 0.001 0.653
Openness 3.76 3.93 3.85 3.99 4.40 0.005 0.004 *
Note. Highest scores that match with blood type traits, and p < 0.05 are highlighted in bold. * p <
0.05 after the Bonferroni’s correction
DISCUSSION AND CONCLUSION
Using blood type personality traits, AI predicted the participants' blood types more accurately
than chance with the exception of one algorithm. We observed a clear and consistent
relationship between blood type and self-reported personality among all four types. The same
traits were also observed in the groups that did not know their blood type, although the
differences were smaller. On the contrary, when using the simplified Big Five personality test
(TIPI-J), AI could not predict the participants' blood type more accurately than chance, and
there was little difference among blood types, which corresponds to the typical past results.
Page 9 of 12
34
Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021
Services for Science and Education – United Kingdom
Previous studies by psychologists found no differences in personality by blood type, and even
if there were differences predicted by blood type, they were thought to be the result of a self- fulfilling prophecy phenomenon [14, 16-17, 20, 28, 35-36, 37-41]. However, when using the
blood type personality traits, the same differences in scores were found in the “no knowledge”
group, although the values were smaller. Therefore, the differences by blood type were most
likely not due to the self-fulfilling prophecy phenomenon, but actually existed, and the
differences in the “no knowledge” group were not due to Type II errors.
In this study, the following four algorithms were used: Multiclass Logistic Regression,
Multiclass Neural Network, Multiclass Decision Jungle, and Multiclass Decision Forest. The first
one showed the highest accuracy for both blood type personality traits and the TIPI-J, which
may indicate that the personality test data are closer to linear than expected, since this
algorithm is mainly used for linear predictions.
These results provide a new, albeit hypothetical, framework for examining how genes influence
human personality. On the other hand, the sample in this study was limited to Japanese
populations, the sample size of the AI training data was small, and the study was used on an
experimental basis. Future studies with larger, more global datasets are needed to clarify the
true impact and to improve algorithms and methodologies.
References
Gerlach, M., Farb, B., Revelle, W., Amaral L. A. N. A robust data-driven approach identifies four personality types
across four large data sets. Nature Human Behaviour, 2018. 2: p. 735-742. https://doi.org/10.1038/s41562-018-
0419-z
Akbar, A. T., Husaini, R., Akbar, B. M., Saifullah, S. A proposed method for handling an imbalance data in
classification of blood type based on Myers-Briggs type indicator. Jurnal Teknologi dan Sistem Komputer, 2020.
8(4): p. 276-283. https://doi.org/10.14710/jtsiskom.2020.13625
Ando, J., Fujisawa, K., Hiraishi, K., Shikishima, C. Kawamoto, T. et al. Psychosocial Twin Cohort Studies in Japan: The
Keio Twin Research Center (KoTReC). Twin Research and Human Genetics, 2019. 22(6): p. 591-596.
https://doi.org/10.1017/thg.2019.109
Lo, M. T., Hinds, D. A., Tung, J., Tung, J. Y., Fanz, C. et al. Genome-wide analyses for personality traits identify six
genomic loci and show correlations with psychiatric disorders. Nature Genetics, 2017. 49: p. 152-156.
https://doi.org/10.1038/ng.3736
Goldberg, L. R. An alternative “description of personality”: the big-five factor structure. Journal of Personality and
Social Psychology, 1990. 59(6): p. 1216–29.
Costa, P. T. Jr, McCrae, R. R. The NEO-P-I-R professional manual: Revised NEO Personality Inventory. (NEO-P-I-R)
and NEO Five-Factor Inventory (Neo-FFI). Odessa, Fla: Psychological Assessment Resources. 1992.
Kunisato, Y., Yamaguchi, A., Suzuki, S. Cloninger's Temperament and Character Model and the Big Five. Japanese
Journal of Personality, 2008. 16(8): p. 323-324.
Diener, E. Subjective well-being. Psychological Bulletin, 1984. 95(3): p. 542–575. https://doi.org/10.1037/0033-
2909.95.3.542
Robins, R. W., Hendin, H. M., Trzesniewski, K. H. Measuring global self-esteem: Construct validation of a single-item
measure and the Rosenberg Self-Esteem scale. Personality and Social Psychology Bulletin, 2001. 27(2): p. 151-161.
https://doi.org/10.1177/0146167201272002
Gosling, S. D., Rentfrow, P. J., Swann, W. B. Jr. A very brief measure of the Big-Five personality domains. Journal of
Research in Personality, 2003. 37(6): p. 504-528. https://doi.org/10.1016/S0092-6566(03)00046-1
Page 10 of 12
35
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
Oshio, A., Abe, S., Cutrone, P. Development, reliability, and validity of the Japanese version of Ten Item Personality
Inventory (TIPI-J). Japanese Journal of Personality, 2012. 21(1): p. 40-52.
https://doi.org/10.2132/personality.21.40
Furukawa T. A Study of Temperament by means of human blood groups. Japanese Journal of Psychology, 1927.
2(4): p. 612-634. https://doi.org/10.4992/jjpsy.2.612
Furukawa T. A study of temperament and blood groups. Journal of Social Psychology, 1930. 1(4): p. 494-509.
https://doi.org/10.1080/00224545.1930.9714153
Nomi M. Understanding compatibility through blood type. Tokyo: Seishun Publishing. 1971.
S. Sato T., Watanabe Y. Psychological studies on blood-typing in Japan. Japanese Psychological Review, 1992.
35(2): p. 234-268. https://doi.org/10.24602/sjpr.35.2_234
Ryu. S. I., Sohn, Y. W. A Review of sociocultural, behavioral, biochemical analyzes on ABO blood-groups typology.
Korean Journal of Social and Personality Psychology, 2007. 21(3): p. 27-55.
https://www.kci.go.kr/kciportal/landing/article.kci?arti_id=ART001077625
Cho, S. H., Suh, E. K. M., Ro, Y. J. Beliefs about blood types and traits and their reflections in self-reported personality.
Korean Journal of Social and Personality Psychology, 2005. 19(11): p. 33-47.
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART00
0977772
Kamise, Y., Matsui, Y. Functions and structure of blood-group stereotype. Bulletin of University of the Sacred Heart,
1994. 82: p. 90-111. https://ci.nii.ac.jp/naid/110000247152/en/
Wu, K., Lindsted K. D., Lee, J. W. Blood type and the five factors of personality in Asia. Personality and Individual
Differeces, 2005. 38(4): p. 797-808. https://doi.org/10.1016/j.paid.2004.06.004
Fuji Television Networks. Nippon no daimondai. Tokyo: Fuji Television Networks. [on aired on November 8,
2015].
Sato, T., Miyazaki, S., Watanabe, Y. An Examination of the Blood Type Personality Relationship Theory (3) From
Stereotype to Prejudice. 2nd convention of Japan Society of Development Psychology, 1991. 2: p. 147.
Sakamoto, A., Yamazaki, K. 2004. Blood-typical personality stereotypes and self-fulfilling prophecy: A natural
experiment with time-series data of 1978-1988. Progress in Asian Social Psychology, 1991. 4: p. 239-262. Seoul:
Kyoyook-KwahakSa.
Alsadi, R. Personality traits and their relationship with blood groups among of Palestinian university students.
International Journal of Psychology and Behavioral Sciences, 2020. 10(2): p. 34-42.
http://article.sapub.org/10.5923.j.ijpbs.20201002.02.html
Cattell, R. B., Young, H. B., Hundleby, J. D. Blood groups and personality traits. American Journal of Human
Genetics, 1964. 16(4): p. 397–402. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1932327/
Cramer, K. M., Imaike, E. Personality, blood type, and the five-factor model. Personality and Individual Differences,
2002. 32(4): p. 621-626. https://doi.org/10.1016/S0191-8869(01)00064-2
Flegr, J., Preiss, M., Klose, J. Toxoplasmosis-associated difference in intelligence and personality in men depends on
their Rhesus blood group but not ABO blood group. PLoS One, 2013. 8: e61272.
https://doi.org/10.1371/journal.pone.0061272
Gupta, S. Blood groups and personality characteristics. Personality and Individual Differences, 1990. 11(3): p. 317-
318. https://doi.org/10.1016/0191-8869(90)90246-N
Jogawar, V. V. Personality correlates of human blood groups. Personality and Individual Differences, 1984. 4(2): p.
215–216. https://doi.org/10.1016/0191-8869(83)90026-0
Kim, B. M., Lee, D. M., Lee, S. H., Gim W. S. Blood-type distribution. Physica A: Statistical Mechanics and its
Applications, 2007. 373(1): p. 533-540. https://doi.org/10.1016/j.physa.2006.05.027
Lester. D., Gatto, J. Personality and blood group. Personality and Individual Differences, 1987. 8: p. 267.
https://doi.org/10.1016/0191-8869(87)90184-X
Page 11 of 12
36
Transactions on Machine Learning and Artificial Intelligence (TMLAI) Vol 9, Issue 6, December - 2021
Services for Science and Education – United Kingdom
Mao, X., Xu, M., Mu, S., Ma Y., He, M. Study on relationship between human ABO blood groups and type A behavior
pattern. Hua Xi Yi Ke Da Xue Xue Bao, 1991. 22(1): p. 93-96.
Nahida, A., Chatterjee, N., Nahida, C. A. A study on relationship between blood group and personality. International
Journal of Home Sciences, 2016. 2(1): p. 239-24.
Patil, J., Kumar, N., Satyam, S. M., Kupusamy, K., Han L. M. et al. Influence of blood group on the character traits - A
cross-sectional study on Malaysian student population. Journal of Chemical and Pharmaceutical Sciences, 2016.
9(2): p. 865-868. https://manipal.pure.elsevier.com/en/publications/influence-of-blood-group-on-the- character-traits-a-cross-sectiona
Sharifi, M., Ahmadian, H., Jalali, A. The relationship between the big five personality factors with blood types in
Iranian university students. Journal of Chemical and Pharmaceutical Research, 2015. 7(5): p. 233-240.
https://www.jocpr.com/abstract/the-relationship-between-the-big-five-personality-factors-with-blood-types- inrniranian-university-students-7553.html
Shimizu, T., Ishikawa, M. Relationships between ABO blood types and personality: Measurement by the Five Factor
model. Kozokoseishugi-kenkyu, 2011. 5: p. 78-91.
Yamaoka S. Discrimination and delusion of blood type personality divination. 18th Annual Meeting of Japan Society
of Personality Psychology, 2009. 18: p. 11.
Nawata, K. No relationship between blood type and personality: Evidence from large-scale surveys in Japan and the
US, Japanese Journal of Psychology, 2014. 85(2): p. 148-156. https://doi.org/10.4992/jjpsy.85.13016
Eysenck, H. J., Nias, D. K. B. Astrology: science or superstition?. London: Curtis Brown Temple Smith. 1982.
Glick, P., Snyder, M. Self-fulfilling prophecy: The psychology of belief in astrology. Humanist, 1986. 46(3): p. 20-24.
Kanazawa, M. A pilot study using AI for psychology: ABO blood type and personality traits. American Journal of
Intelligent Systems, 2021. 11(1): p. 1-7. http://article.sapub.org/10.5923.j.ajis.20211101.01.html
Matsui, Y. A statistical analysis of personality difference by blood type. Bulletin of Tokyo Metropolitan Tachikawa
Junior College, 1991. 24: p. 51-54.
Muto, C., Nagashima, M., Harada, J., Abe, S., Furuya, Y., Kamizon, K., Konishi, Y. A demonstrative and critical study
on pseudo-science for scientific literacy construction at teacher education course. Grants-in-Aid for Scientific
Research FY2011 Final Research Report (Japan), 2012. https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT- 22650191/
Tsuchimine, S., Saruwatari, J., Kaneda, A., Yasui-Furukori, N. ABO blood type and personality traits in healthy
Japanese subjects. PLoS ONE, 2015. 10: e0126983. https://doi.org/10.1371/journal.pone.0126983.
Hobgood, D. K. Personality traits of aggression-submissiveness and perfectionism associate with ABO blood groups
through catecholamine activities. Medical Hypotheses, 2011. 77(2): p. 294-300.
https://doi.org/10.1016/j.mehy.2011.04.039
Hobgood, D. K. ABO B gene is associated with introversion personality tendencies through linkage with dopamine
beta hydroxylase gene. Medical Hypotheses, 2021. 148: 110513. https://doi.org/10.1016/j.mehy.2021.110513.
Kawamoto, T., Oshio, A., Abe, S., Tsubota, Y., Hirashima, T., Ito, H., Tani, I. Age and Gender Differences of Big Five
Personality Traits in a Cross-Sectional Japanese Sample. Japanese Journal of Developmental Psychology, 2015.
26(2): p. 107-122. https://doi.org/10.11201/jjdp.26.107
Lehmann, R., Denissen, J. J., Allemand, M., Penke, L. Age and gender differences in motivational manifestations of
the Big Five from age 16 to 60. Developmental Psychology, 2013. 49(2): p. 365-383.
https://doi.org/10.1037/a0028277
Soto, C. J., John, O. P., Gosling, S. J., Potter, J. Age differences in personality traits from 10 to 65: Big Five domains and
facets in a large cross-sectional sample. Journal of Personality and Social Psychology, 2011. 100(2): p. 330-348.
https://doi.org/10.1037/a0021717
Weisberg, Y. J., Deyoung, C. G., Hirsh, J. B. Gender Differences in Personality across the Ten Aspects of the Big Five.
Frontiers in Psychology, 2011. 2: p. 178. https://doi.org/10.3389/fpsyg.2011.00178
Page 12 of 12
37
Kanazawa, M. (2021). AI-based Analysis on Relationship between Genes and Personality: Evaluation Results with the ABO Blood Type. Transactions
on Machine Learning and Artificial Intelligence, 9(6). 26-37.
URL: http://dx.doi.org/10.14738/tmlai.96.11290.
Okubo, Y. Pretransfusion Testing with Special Reference to Blood Groups in Japanese (2nd ed.). Tokyo: Ishiyaku
Publishers. 1997.
Cohen, J. Statistical Power Analysis for the Behavioral Sciences. New York, NY: Academic Press. 1977.