How satisfied are patients with nursing care and why? A comprehensive study based on social media and opinion mining

ABSTRACT

To assess the overall experience of a patient in a hospital, many factors must be analyzed; nonetheless, one of the key aspects is the performance of nurses as they closely interact with patients on many occasions. Nurses carry out many tasks that could be assessed to understand the patient’s satisfaction and consequently, the effectiveness of the offered services. To assess their performance, traditionally, expensive, and time-consuming methods such as questionnaires and interviews have been used; nevertheless, the development of social networks has allowed the patients to convey their opinions in a free and public manner. For that reason, in this study, a comprehensive analysis has been performed based on patients’ opinions collected from a feedback platform for health and care services, to discover the topics about nurses the patients are more interested in. To do so, a topic modeling technique has been proposed. After this, sentiment analysis has been applied to classify the topics as satisfactory or unsatisfactory. Finally, the results have been compared with what the patients think about doctors. The results highlight what topics are most relevant to assess the patient satisfaction and to what extent. The results remark that the opinion about nurses is, in general, more positive than about doctors.

KEYWORDS:

• Patient satisfaction
• patient feedback
• nurse-patient relation
• topic modeling
• sentiment analysis

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

¹ https://www.careopinion.org.uk

² https://wordnet.princeton.edu

Additional information

Funding

This work has been partially supported by FEDER and the State Research Agency (AEI) of the Spanish Ministry of Economy and Competition under grant SAFER: PID2019-104735RB-C42 [AEI/FEDER, UE]. the General Subdirection for Gambling Regulation of the Spanish Consumption Ministry under the grant Detec-EMO:SUBV23/00010, and the project TED2021-130682B-100 funded byMCIN/AEI/10.13039/501100011033 and by the European Union Next Generation EU/ PRTR.