Abstract
Implicit motives are key drivers of individual differences but are time-consuming to assess, requiring many hours of work by trained human coders. In this paper we report on the use of machine learning to automate the coding of implicit motives. We assess the performance of three neural network models on three unseen datasets in order to establish baselines for convergent, divergent, causal, and criterion validity. Results suggest that this is a promising direction to pursue in developing an automatic procedure for coding implicit motives.
Similar content being viewed by others
Notes
An example of an implementation of automated coding can be found at www.implicitmotives.com.
To our knowledge, there are only two available investigations on automating implicit motive coding using a machine-learning approach. Additionally, there has been some work by Felix Schönbrodt which was not available to us at the time we submitted this manuscript. Both the investigations that were available are student theses and were unpublished at the time of this writing. In his Ph.D. thesis, Halusic (2015) attempted to develop an automated coding system for nAch by creating a set of synonym-based word vectors. His approach can be classified as a variant of the bag-of-words approach, which is in contrast to our more data-driven approach, since the features of our models were not built around particular sets of target words. While Halusic was able to obtain rs in the .5 region between machine-coded and human-coded scores, he was unable to demonstrate either predictive or causal validity for model-predicted scores. In a masters thesis on automating PSE coding for the Winter (1994) motives, Adler (2017)’s main goal was to arrive at a binary classification system, namely, to predict whether a text was generated by someone in the motive-arousal condition or in the non-aroused (“control”) condition in an experiment. Thus, his research objective was different from ours, in that he did not seek to develop a machine-learning algorithm that could predict the motive score of an individual in an unseen dataset.
Regarding this second advantage, while it would still be possible for human coders to code archival material, the financial cost and time burden of relying on human researchers to code unstructured texts (i.e., material that was not generated in the context of a standardized motive measure such as the PSE) would be much higher than feeding such texts into a machine.
Due to conflicts with study timing and coder availability, we were unable to obtain motive scores for the same set of 30 stories from the other 3 coders, however each of these three coders individually accounted for approximately 5% of the dataset.
Ring and Pang (2017) presented preliminary findings from machine-learning experiments at a talk at Friedrich-Alexander University in Erlangen, Germany. They inserted part-of-speech information using WordNet (Miller 1995; Fellbaum 1998), employed a bag-of-words approach, and tested 11 machine-learning algorithms using tenfold nested cross-validation. Their findings indicated that part-of-speech information only improved validation accuracy minimally, on average by 4%.
To aid future automation research, the structure of the three models we built, the unseen datasets, and a Python script to replicate the results we report are available here: https://osf.io/563xn/?view_only=6870e14b364743a688ff17fea80f2c59.
References
Adler, T. (2017). Automated encoding of motives in psychological picture story exercises. Master’s Thesis, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen.
Allen, C., & Hospedales, T. M. (2019). Analogies explained: Towards understanding word embeddings. Proceedings of the 36th international conference on machine learning, Long Beach, California, PMLR 97, June 2019. http://arxiv.org/abs/1901.09813
Apers, C., Lang, J. W. B., & Derous, E. (2019). Who earns more? Explicit traits, implicit motives and income growth trajectories. Journal of Vocational Behavior,110, 214–228. https://doi.org/10.1016/j.jvb.2018.12.004.
Awford, J. (2016). 'We can shoot your wife and frame your mother-in-law': The ad by a small picture framing business BANNED for being 'violent'… or is it just a bad joke? Daily Mail UK Online. Retrieved from March 22, 2016 from https://www.dailymail.co.uk/news/article-3504544/Joke-slogan-shooting-wife-banned.html
Bai, S., Kolter, J.Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. http://arxiv.org/abs/1803.01271
Benjamini, Y., & Hochberg, Y. (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of Royal Statistical Society Series B (Mehodological),57, 289–300. https://doi.org/10.1111/j.2517-6161.1995.tb02031.x.
Borsboom, D., Mellenbergh, G., & Heerden, J. (2004). The concept of validity. Psychological Review,111, 1061–1071. https://doi.org/10.1037/0033-295X.111.4.1061.
Busch, H. (2018). Power motivation. In J. Heckhausen & H. Heckhausen (Eds.), Motivation and action (3rd ed., pp. 335–368). New York: Springer.
Cheng, W. (2013). Semantic prosody. In C. A. Chapelle (Ed.), The encyclopedia of applied linguistics (pp. 1–7). Hoboken: Wiley-Blackwell.
Ditlmann, R. K., Purdie-Vaughns, V., Dovidio, J. F., & Naft, M. J. (2017). The implicit power motive in intergroup dialogues about the history of slavery. Journal of Personality and Social Psychology, 112(1), 116–135. https://doi.org/10.1037/pspp0000118.
Dufner, M., Arslan, R. C., & Denissen, J. J. A. (2018). The unconscious side of Facebook: Do online social network profiles leak cues to users’ implicit motive dispositions? Motivation and Emotion,42, 79–89. https://doi.org/10.1007/s11031-017-9663-1.
Fellbaum, C. (Ed.). (1998). WordNet: An electronic lexical database. Cambridge, MA: MIT Press.
Firth, J. R. (1957). A synopsis of linguistic theory, 1930–55. In F. R. Palmer (Ed.), Studies in linguistic analysis (pp. 1–32). Oxford: The Philological Society.
Fodor, E. M., & Riordin, J. M. (1995). Leader power motive and group conflict as influences on leader behavior and group member self-affect. Journal of Research in Personality,29, 418–431. https://doi.org/10.1006/jrpe.1995.1024.
Fodor, E. M., Wick, D. P., & Conroy, N. E. (2012). Power motivation as an influence on reaction to an imagined feminist dating partner. Motivation and Emotion,36, 301–310. https://doi.org/10.1007/s11031-011-9254-5.
Furley, P., Schweizer, G., & Wegner, M. (2019). The power motive as a predictor of receptiveness to nonverbal behavior in sport. Motivation and Emotion,43, 917–928. https://doi.org/10.1007/s11031-019-09788-4.
Goldberg, Y. (2015). A Primer on neural network models for natural language processing. Retrieved October 22, 2019, from http://arxiv.org/abs/1510.00726v1
Hagemeyer, B., Neberich, W., Asendorpf, J. B., & Neyer, F. J. (2013). (In)congruence of implicit and explicit communal motives predicts the quality and stability of couple relationships. Journal of Personality,81(4), 390–402. https://doi.org/10.1111/jopy.12016.
Halusic, M. (2015). Developing a computer coding scheme for the implicit achievement motive. Ph.D. Thesis, University of Missouri-Columbia, July.
Harris, Z. S. (1954). Distributional structure. Word,10(23), 146–162. https://doi.org/10.1080/00437956.1954.11659520.
Hauser, D., & Schwarz, N. (2016). Semantic prosody and judgment. Journal of Experimental Psychology General,145, 882–896. https://doi.org/10.1037/xge0000178.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. CoRR, http://arxiv.org/abs/1502.01852
Heckhausen, H. (1963). Hoffnung und Furcht in der Leistungsmotivation (Hope and fear components of achievement motivation). Anton Hain.
Hofer, J., & Busch, H. (2019). Women in power-themed tasks: Need for power predicts task enjoyment and power stress. Motivation and Emotion,43, 740–757. https://doi.org/10.1037/a0020053.
Hogenraad, R. (2005). What the words of war can tell us about the risk of war. Peace and Conflict: Journal of Peace Psychology,11, 137–151. https://doi.org/10.1207/s15327949pac1102_2.
Jackson, D. N. (1984). Personality research form manual (3rd ed.). Port Huron: Sigma Assessment Systems.
Johnson, P. B. (1981). Achievement motivation and success: Does the end justify the means? Journal of Personality and Social Psychology,40(2), 374–375. https://doi.org/10.1037/0022-3514.40.2.374.
Kalchbrenner, N., Espeholt, L., Simonyan, K., van den Oord, A., Graves, A., & Kavukcuoglu, K. (2016). Neural machine translation in linear time. CoRR, http://arxiv.org/abs/1610.10099
Khurana, D., Koli, A., Khatter, K., & Singh, S. (2017). Natural language processing: State of the art, current trends and challenges. CoRR, http://arxiv.org/abs/1708.05148
Kim, Y. (2014). Convolutional neural networks for sentence classification. Proceedings of the 2014 Conference on empirical methods in natural language processing (EMNLP) (pp. 1746–1751). Association for Computational Linguistics. https://doi.org/10.3115/v1/D14-1181
Klimt, B., & Yang, Y. (2004). The Enron Corpus: A new dataset for email classification research. In J. F. Boulicault, F. Esposito, F. Giannotti, & D. Pedreschi (Eds.). Machine learning: ECML 2004. Lecture Notes in Computer Science (vol. 3201). Springer.
Koo, T. K., & Li, M. Y. (2016). A guideline of selecting and reporting intraclass correlation coefficients for reliability research. Journal of Chiropractic Medicine,15(2), 155–163. https://doi.org/10.1016/j.jcm.2016.02.012.
Krause, J., Perer, A., & Ng, K. (2016). Interacting with predictions: Visual inspection of black-box machine learning models. Proceedings of the 2016 CHI Conference on human factors in computing systems (pp. 5686–5697). https://doi.org/10.1145/2858036.2858529
Kuhl, J. (1978). Situations-, reaction-, and person-related consistency of achievement motive according to Heckhausen TAT. Archiv Für Psychologie,130(1), 37–52.
Kuhl, J., & Scheffer, D. (1999). Der operante multi-motive-test (OMT): Manual (The operant multi-motive-test (OMT): Manual). Osnabrück: University of Osnabrück.
Lea, C., Vidal, R., Reiter, A., & Hager, G.D. (2016). Temporal convolutional networks: A unified approach to action segmentation. CoRR, http://arxiv.org/abs/1608.08242
Leber, J. (2013). The immortal life of the Enron e-mails. Technology Review. Retrieved from July 2, 2013 from https://www.technologyreview.com/s/515801/the-immortal-life-of-the-enron-e-mails/
Li, X., Chen, S., Hu, X., & Yang, J. (2018). Understanding the disharmony between dropout and batch normalization by variance shift. CoRR, http://arxiv.org/abs/1801.05134
Louw, B. (1993). Irony in the text or insincerity in the writer? The diagnostic potential of semantic prosodies. In G. Francis & E. Tognini-Bonelli (Eds.), Text and technology: In honour of John Sinclair (pp. 157–176). Amsterdam: John Benjamins Publishing.
McClelland, D. C. (1975). Power: The inner experience. New York: Irvington.
McClelland, D. C., Atkinson, J. W., Clark, R. A., & Lowell, E. L. (1953). The achievement motive. New York: Appleton-Century-Crofts.
McClelland, D. C., Koestner, R., & Weinberger, J. (1989). How do self-attributed and implicit motives differ? Psychological Review,96(4), 690–702. https://doi.org/10.1037/0033-295X.96.4.690.
Méndez, G., Hinrichs, U., & Nacenta, M. (2017). Bottom-up vs. Top-down: Trade-offs in efficiency, understanding, freedom and creativity with InfoVis tools. Proceedings of the 2017 CHI conference on human factors in computing systems (pp. 841–852). https://doi.org/10.1145/3025453.3025942
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. CoRR, http://arxiv.org/abs/1301.3781
Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., & Joulin, A. (2017). Advances in pre-training distributed word representations. CoRR, http://arxiv.org/abs/1712.09405
Miller, G. A. (1995). WordNet: A lexical database for English. Communications of the ACM, 38(11), 39–41.
Morgan, C. D., & Murray, H. A. (1935). A method for investigating fantasies: The thematic apperception test. Archives of Neurology and Psychiatry,34, 289–306.
Mrksic, N., Vulić, I., Séaghdha, D., Leviant, I., Reichart, R., Gašić, M., Korhonen, A., & Young, S. (2017). Semantic specialisation of distributional word vector spaces using monolingual and cross-Lingual constraints. Retrieved from http://arxiv.org/abs/1706.00374
Ngo, T. A. (2019). Developing a hierarchical model of personality and motivation to predict youth volunteerism: A cross-culture study. Doctoral thesis, Nanyang Technological University, Singapore
Nickel, M., & Kiela, D. (2017). Poincaré embeddings for learning hierarchical representations. CoRR, http://arxiv.org/abs/1705.08039
Pang, J. S., & Kang, N. Q. (2016). Effects of a brief short-term self-administered mindfulness-based intervention program on young adults’ life satisfaction, psychological need satisfaction, and attentional control. The Stockholm Criminology Symposium, Stockholm, Sweden
Pang, J. S., Villacorta, M. A., Chin, Y. S., & Morrison, F. J. (2009). Achievement motivation in the social context: Implicit and explicit hope of success and fear of failure predict memory for and liking of successful and unsuccessful peers. Journal of Research in Personality,43(6), 1040–1052. https://doi.org/10.1016/j.jrp.2009.08.003.
Pennebaker, J. W., Francis, M. E., & Booth, R. J. (2001). Linguistic inquiry and word count (LIWC): LIWC2001. Mahwah: Lawrence Erlbaum Associates.
Pennebaker, J. W., & King, L. A. (1999). Linguistic styles: Language use as an individual difference. Journal of Personality and Social Psychology,77, 1296–1312. https://doi.org/10.1037/0022-3514.77.6.1296.
Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global vectors for word representation. In Empirical methods in natural language processing (EMNLP), 1532–1543. Retrieved October 18, 2018 from https://www.aclweb.org/anthology/D14-1162.
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations
Raihala, C., & Hansen, G. (2019). Power stress in primary school children. Motivation and Emotion,43, 82–92. https://doi.org/10.1007/s11031-018-9724-0.
Ramsay, J. E. (2014). Refining the picture story exercise: Towards a better understanding of hope, fear, and the achievement motive. Doctoral Thesis, Nanyang Technological University, Singapore
Ramsay, J. E., & Pang, J. S. (2013). Set ambiguity: A key determinant of reliability and validity in the picture story exercise. Motivation and Emotion,37(4), 661–674. https://doi.org/10.1007/s11031-012-9339-9.
Riach, D. (2019). Determinism in deep learning. Gpu Technology Conference 2019. https://bit.ly/dl-determinism-slides-v2 (updated 2019–05–17). Retrieved October 17, 2019, from https://developer.nvidia.com/gtc/2019/video/S9911
Ring, H., & Pang, J. S. (2017). Toward automatic coding of implicit motives via machine learning. Invited talk given at Institute of Psychology, Experimental Psychology, Motivation and Affective Neuroscience, Friedrich-Alexander University. Erlangen, Germany.
Safyer, P., Volling, B. L., Schultheiss, O. C., & Tolman, R. M. (2019). Adult attachment, implicit motives, and mothers’ and fathers’ parenting behaviors. Motivation Science,5(3), 220–234. https://doi.org/10.1037/mot0000112.
Schönbrodt, F. D., & Gerstenberg, F. X. R. (2012). An IRT analysis of motive questionnaires: The Unified Motive Scales. Journal of Research in Personality,46, 725–742. https://doi.org/10.1016/j.jrp.2012.08.010.
Schultheiss, O. C. (2001). Manual for the assessment of hope of success and fear of failure (English translation of Heckhausen’ s need Achievement measure). Ann Arbor: Department of Psychology, University of Michigan.
Schultheiss, O. C. (2013). Are implicit motives revealed in mere words? Testing the marker-word hypothesis with computer-based text analysis. Frontiers in Psychology. https://doi.org/10.3389/fpsyg.2013.00748.
Schultheiss, O. C., & Brunstein, J. (Eds.). (2010). Implicit motives. Oxford: Oxford University Press.
Schultheiss, O. C., & Pang, J. S. (2007). Measuring implicit motives. In R. W. Robins, R. C. Fraley, & R. F. Krueger (Eds.), Handbook of research methods in personality psychology (pp. 322–344). New York: The Guilford Press.
Schultheiss, O. C., Yankova, D., Dirilikvo, B., & Schad, D. J. (2009). Are implicit and explicit motive measures statistically Independent? A fair and balanced test using the Picture Story Exercise and a cue- and response-matched questionnaire measure. Journal of Personality Assessment,91(1), 72–81. https://doi.org/10.1080/00223890802484456.
Shen, L., Satta, G., & Joshi, A. (2007). Guided learning for bidirectional sequence classification. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. Retrieved March 5, 2020 from https://www.aclweb.org/anthology/P07-1096
Shrout, P. E., & Fleiss, J. L. (1979). Intraclass correlations: Uses in assessing rater reliability. Pyschological Bulletin,86, 420–428. https://doi.org/10.1037/0033-2909.86.2.420.
Smith, M. S. (1968). The computer and the TAT. Journal of School Psychology,6, 206–214. https://doi.org/10.1016/0022-4405(68)90017-4.
Smith, C. P., Ryan, E. R., & Diggins, D. R. (1972). Moral decision making: Cheating on examinations. Journal of Personality,40, 640–660.
Stoeckart, P. F., Strick, M., Bijleveld, E., & Aarts, H. (2018). The implicit power motive predicts decisions in line with perceived instrumentality. Motivation and Emotion,42, 309–320. https://doi.org/10.1007/s11031-018-9687-1.
Stone, P. J., Dunphy, D. C., Smith, M. S., & Ogilvie, D. M. (1966). The general inquirer: A computer approach to content analysis. Cambridge, MA: MIT Press.
Swinger, N., De-Arteaga, M., Heffernan, N. T., Leiserson, M. D. M., & Kalai, A. T. (2018). What are the biases in my word embedding? http://arxiv.org/abs/1812.08769
Thielgen, M. M., Krumm, S., & Hertel, G. (2015). When being old pays off: Age mitigates adverse effects of low implicit–explicit motive congruency on work motivation. Journal of Career Assessment,23(3), 459–480. https://doi.org/10.1177/1069072714547613.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. CoRR, http://arxiv.org/abs/1706.03762
Vulic, I., & Mrksic, N. (2017). Specialising word vectors for lexical entailment. CoRR, http://arxiv.org/abs/1710.06371
Weinberger, J., Cotler, T., & Fishman, D. (2010). The duality of affiliative motivation. In O. C. Schultheiss & J. C. Brunstein (Eds.), Implicit motives (pp. 71–88). Oxford: Oxford University Press.
Weitzel, L., Prati, R., & Aguiar, R. (2016). The comprehension of figurative language: What is the influence of irony and sarcasm on NLP techniques? In W. Pedrycz & S.-M. Chen (Eds.), Sentiment analysis and ontology engineering. New York: Springer.
Whitley, B. E. J. (1998). Factors associated with cheating among college students: A review. Research in Higher Education,39, 235–274.
Winter, D. G. (1973). The power motive. Mumbai: Free Press.
Winter, D. G. (1994). Manual for scoring motive imagery in running text. Unpublished Instrument. Ann Arbor: University of Michigan.
Winter, D. G. (2010). Why achievement motivation predicts success in business but failure in politics: The importance of personal control. Journal of Personality,78(6), 1637–1667. https://doi.org/10.1111/j.1467-6494.2010.00665.x.
Wolf, M., Horn, A., Mehl, M., Haug, S., Pennebaker, J. W., & Kordy, H. (2008). Computergestützte quantitative Textanalyse: Äquivalenz und Robustheit der deutschen version des linguistic inquiry and word count (Computer-aided quantitative text analysis: Equivalence and reliability of the German adaptation of the linguistic inquiry and word count). Diagnostica,2, 85–98. https://doi.org/10.1026/0012-1924.54.2.85.
Yapo, A., & Weiss, J. (2018). Ethical implications of bias in machine learning. Proceedings of the 51st Hawaii International Conference on System Sciences (pp. 5365–5372). Retrieved February 28, 2020 from https://hdl.handle.net/10125/50557.
Yu, L-C, Wang, J., Lai, K.R., & Zhang, X. (2017). Refining word embeddings for sentiment analysis. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (pp. 545–550). Copenhagen:Association for Computational Linguistics
Zhang, Y., & Wallace, B.C. (2016). A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. http://arxiv.org/abs/1510.03820v4
Acknowledgements
We would like to thank Oliver C. Schultheiss, Jonathan E. Ramsay, Thuy-Anh Ngo, Rena Ng, and Tingxuan Leng for sharing their data with us, and Veronika Brandstätter for reviewing a previous version of this manuscript.
Author information
Authors and Affiliations
Contributions
The two authors are equal contributors, and order of names is alphabetical. Both authors contributed equally to conception and design. Dataset compilation, preparation, and statistical analyses were performed by Joyce S. Pang. Dataset processing and machine learning scripts were written by Hiram Ring. The first draft of the manuscript was written by Joyce S. Pang and both authors commented on and revised subsequent versions of the manuscript. Both authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Pang, J.S., Ring, H. Automated coding of implicit motives: A machine-learning approach. Motiv Emot 44, 549–566 (2020). https://doi.org/10.1007/s11031-020-09832-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11031-020-09832-8