27
03/17 PERSONALquarterly
SUMMARY
Research question:
Is it possible to predict personality traits from
social media data?
Methodology:
Comparison of machine learning based predictive algo-
rithms based on an empirical social media dataset from Xing.
Practical implications:
Algorithms for predicting personality traits
are useful in eRecruiting systems saving costs and time.
LITERATURVERZEICHNIS
Biemann, T./Weckmüller, H. (2012): Methoden der Personalauswahl: Was
nützt? PERSONALquarterly 46(1): 46-49.
Buettner, R. (2014a): A Framework for Recommender Systems in Online
Social Network Recruiting. In: HICSS 2014 Proceedings: 47th Hawaii Internati-
onal Conference on System Sciences (HICSS-47), Januar 6-9, 2014, Big Island,
Hawaii, pp. 1415–1424.
Buettner, R. (2014b): efficientRecruiting 2.0 - Effizientes Recruiting von Fach-
kräften im Web 2.0. In BITKOM KnowTech 2014 Proceedings, October 15-16,
2014, Hanau, Germany, pp. 119–127.
Buettner, R. (2016c): Mining a user‘s personality from social media data: A
comparison between the random forest and the C4.5 J48 based approach. In VHB
2016 Proceedings: 78. Wissenschaftliche Jahrestagung des Verbandes der Hoch-
schullehrer für Betriebswirtschaft (VHB), May 18-20, 2016, Munich, Germany.
Buettner, R. (2016e): Personality as a predictor of business social media
usage: An empirical investigation of XING usage patterns. In PACIS 2016 Pro-
ceedings: 20th Pacific Asia Conference on Information Systems (PACIS), June
27 - July 1, Chiayi, Taiwan.
Buettner, R. (2016g): Innovative Personality-based Digital Services. In PACIS
2016 Proceedings: 20th Pacific Asia Conference on Information Systems (PA-
CIS), June 27 - July 1, Chiayi, Taiwan.
Buettner, R. (2016h): Predicting user behavior in electronic markets based
on personality-mining in large online social networks: A personality-based
product recommender framework. Electronic Markets: The International Journal
on Networked Business, 2016, pp. 1-19.
Costa, P. T./McCrae, R. R. (1992): Revised NEO personality inventory (NEO-
PI-R) and the NEO Five-Factor inventory (NEO-FFI): Professional manual. PAR,
Odessa, FL, USA.
Edwards, J. R. (1991): Person-job fit: A conceptual integration, literature
review, and methodological critique. International review of industrial and
organizational psychology. In: International review of industrial and organiza-
tional psychology. Cooper CL, Robertson IT (Ed.). Vol. 6. Oxford: John Wiley &
Sons, pp. 283–357.
Gosling, S. D./Rentfrow, P. J./Swann Jr., W. B. (2003): A very brief measure
of the Big-Five personality domains. Journal of Research in Personality 37 (6),
504–528.
Kuhn, M./Johnson, K. (2013): Applied Predictive Modeling. New York: Springer.
Kristof, A. L. (1996): Person-organization fit: An integrative review of its
conceptualizations, measurement, and implications. Personnel Psychology 49
(1): 1–49.
Kristof-Brown, A. L./Zimmerman, R. D./Johnson, E. C. (2005): Consequences
of individuals’ fit at work: A meta-analysis of person-job, person-organization,
person-group, and person-supervisor fit. Personnel Psychology 58 (2): 281–342.
Quinlan, J. R. (1993): C4.5: Programs for Machine Learning. San Mateo, CA:
Morgan Kaufmann.
R Core Team (2015): R: A Language and Environment for Statistical Compu-
ting. R Foundation for Statistical Computing. Vienna, Austria.
Verquer, M. L./Beehr, T. A./Wagner, S. H. (2003): A meta-analysis of rela-
tions between person-organization fit and work attitudes. Journal of Vocational
Behavior 63 (3): 473–489.
Werbel, J. D./Johnson, D. J. (2001): The Use of Person-Group Fit for Employ
ment Selection: A Missing Link in Person-Environment Fit. Human Resource
Management 40 (3): 227–240.
PROF. DR. RICARDO BÜTTNER
Professur für Data Science an der Fakultät für
Betriebswirtschaft
Hochschule Aalen
E-Mail:
gorithmen der person-organization fit und der person-group fit
geschätzt werden können. Schließlich wurden Arbeitnehmerri-
siken durch den Einsatz solcher Algorithmen genannt.
Es bleibt jedoch abzuwarten, inwieweit prädiktive Algorith-
men mit etablierten Personalauswahlinstrumenten mithalten
können und wenn dies tatsächlich der Fall sein sollte, ob Per-
sonalverantwortliche prädiktive Algorithmen tatsächlich ein-
setzen werden. Wie Biemann und Weckmüller (2012) gezeigt
haben, ist „in keiner anderen personalwirtschaftlichen Teil-
funktion … der Unterschied zwischen wissenschaftlichen Er-
kenntnissen und Einschätzung von Personalverantwortlichen
so groß wie bei der Bewertung der Nützlichkeit und Qualität
von Personalauswahlinstrumenten“ (S. 49).
