Introduction: Opinion mining has been receiving increasing attention from a broad range of scientific communities since early 2000s. The present study aims to systematically investigate the intellectual structure of opinion mining research. Method: Using topic search, citation expansion, and patent search, we collected 5,596 bibliographic records of opinion mining research. Then, intellectual landscapes, emerging trends, and recent developments were identified. We also captured domain-level citation trends, subject category assignment, keyword co-occurrence, document co-citation network, and landmark articles. Analysis: Our study was guided by scientometric approaches implemented in CiteSpace, a visual analytic system based on networks of co-cited documents. We also employed a dual-map overlay technique to investigate epistemological characteristics of the domain. Results: We found that the investigation of algorithmic and linguistic aspects of opinion mining has been of the community's greatest interest to understand, quantify, and apply the sentiment orientation of texts. Recent thematic trends reveal that practical applications of opinion mining such as the prediction of market value and investigation of social aspects of product feedback have received increasing attention from the community. Conclusion: Opinion mining is fast-growing and still developing, exploring the refinements of related techniques and applications in a variety of domains. We plan to apply the proposed analytics to more diverse domains and comprehensive publication materials to gain more generalized understanding of the true structure of a science.