Assessment of Career Adaptability: Combining Text Mining and Item Response Theory Method

Abstract

Recently, combined quantitative and qualitative analysis has become popular for research. In studying careers, subjective and objective information are ideal for assessing individual career development and are relevant in career counseling. This paper measures career adaptability by combining text mining and item response theory (IRT), with college students' self-reported career adaptability as a subjective measure and responses to questionnaire items as an objective measure. The two are combined under a Bayesian framework. Additionally, the validity of text categorization and IRT, combined with model measurement, were explored; text categorization results were used as prior information when estimating IRT capability parameters to test whether adding prior information can improve accuracy. This study draws the following conclusions: (1) The text classification method had the highest sensitivity in 300-person samples; however, the text-IRT method had the best predictive effect, high reliability, and unique advantages in accuracy. (2) In 600-person samples, the text classification method had the best predictive effect. The effect was relatively good, with unique advantages in identifying low career adaptability. However, this must be selected according to actual needs. If the accuracy requirement is high and sensitivity can be sacrificed, the text-IRT method is more appropriate. (3) The text-IRT method is more suitable for 900 subjects when accuracy, sensitivity, and specificity need to be considered, and text classification is best when identifying low career adaptability. (4) Sample size influenced accuracy, specificity, and the negative predictive values of text classification, as well as the sensitivity of IRT and text-IRT methods.INDEX TERMS Career adaptability, item response theory, text mining.

Proactive Personality Measurement Using Item Response Theory and Social Media Text Mining

“…Based on the analysis of formula (3), y denotes the score of an individual; g θ |y represents the analysis model based on the individual score; α and β, respectively, denote the discrimination parameter and the difficulty parameter; and P (x|θ , α, β) represents the likelihood function of the algorithm (He, 2013;Zhang et al, 2019).…”

“…The prior distribution P (θ ) should also be considered; therefore, θ is the best when P (X|θ ) P (θ ) has achieved the maximum value (Helin and Burger, 2015). Because P (X) (the prior distribution of X) is fixed (which can be obtained by analyzing the questionnaire), the maximization function (He, 2013;Zhang et al, 2019) can be changed into:…”

“…According to the Bayesian principle, P (θ ) must be maximized; the maximum posterior probability estimation (He, 2013;Zhang et al, 2019) is, argmaxP (θ |X) = argmax P(X|θ )P(θ )…”

Discovery Model Based on Analogies for Teaching Computer Programming

“…Another important area of machine learning is deep learning [43,44], natural language processing (NLP) [25], and text mining, which are computer and statistical techniques developed in the early nineties [45] used to discover new non-explicit information in source documents [46,47] and was aimed at discovering patterns through the right combination of artificial intelligence, machine learning, statistics, and data mining [48]. Text mining is currently used for various operations such as in image analysis [49], in biomedical fields (hospitals and clinics) [50,51], in the analysis of profiles of university students [52], in geosciences (geology, geophysics, geochemistry and remote sensing) [53], and in the automotive sector [54], among others.…”

An Effective Attributes Mining for Larger Dataset using Neural Network

“…For the assessment of the proposed method, 20 diverse content reports are utilized to perform numerous assaults, for example, organizing, addition, and cancellation assaults. This paper [6] estimates career versatility by consolidating text mining and item response theory (IRT), with undergrads' selfannounced profession flexibility as an abstract measure and reactions to poll things as a goal measure. The two are consolidated under a Bayesian framework.…”