Electronic Opinion Analysis in Organizational Culture Audit

Abstract

Organizational culture defines an organization’s uniqueness and identity. It is made up of values, beliefs, attitudes, norms, and patterns of behavior that are shared and adopted by individuals in the organization to cope with internal and external pressure. Computerized culture audit system is more cost efficient, time saving and is less prone to error. However, one of the challenges faced is the difficulty in obtaining accurate employee opinions from free texts. The existing sentiment analysis methods available cannot effectively be applied directly to the organizational culture context for employee opinion analysis. Therefore, this study proposes an employee opinion analysis method known as “Opinion Keyword Extraction” which is based on building customized corpus specific for sentiment analysis in organizational culture context. Opinion Keyword Extraction is a combination of the rule-base and lexicon approach using our own corpus datastore. The customized corpus consists of features related to negation detection, detection of special words relevant to organizational culture and detection of emotion symbols. We evaluated our method using primary data collected from 100 participants and found that our Opinion Keyword Extraction method performed better in comparison with existing methods.