Artificial intelligence in service industries: customers’ assessment of service production and resilient service operations

Figures & data

Table 1. Variables’ description.

Variable	Description
Overall_Experience_Score	It is the overall experience rating score provided by the online reviewer (ranging from 1 to 5) which captures her overall level of satisfaction with the service experience.
AI-empowered_delivery_service_Pos	It is a dummy variable equal to 1 if the online reviewer has provided a statement related to AI-empowered delivery services which is associated with a positive sentiment polarity score. It is equal to zero otherwise.
AI-empowered_delivery_service_Neg	It is a dummy variable equal to 1 if the online reviewer has provided a statement related to AI-empowered delivery services which is associated with a negative sentiment polarity score. It is equal to zero otherwise.
Control Indicators
Average_Observed_Score	It represents the score observed by the online reviewer on TripAdvisor before submitting her review.
Submission_Mobile	It represents the device used by the online reviewer to submit her OR. In particular, it is equal to 1 if the reviewer has used a mobile device, and zero if desktop.
Written_Reviews	It denotes the number of reviews posted on TripAdvisor by the reviewer.
Absence_ID_Details	It is a dummy variable equal to 1 if the reviewer has not agreed to share either her age or her gender, 0 otherwise.
Sentiment_Polarity_Overall_Score	It is a continuous variable ranging from −1 (extremely negative) to +1 (extremely positive) which contains the sentiment polarity score associated to the entire text of the OR (Hutto and Gilbert 2014).
Review_Length	It denotes the number of words embedded in the OR.
Review_Year	It is a numeric variable which identifies the year when the OR was originally submitted. In the model it has been operationalised as a set of dummy variables (one for each year except for the first year of observations).
Firm_Identifier	It denotes a identifier that is unique to each firm in the dataset.
Firm_Org_Structure	It is a dummy variable that assumes the value of 1 when the firm belongs to a chain and zero otherwise.
Firm_Category	It refers to a categorical variable ranging from 1 to 5 which classifies firms based on their category.

Table 2. Descriptive statistics.

	Mean/proportion	SD	Min	Max
Overall_Experience_Score	4.393	1.007	1.000	5.000
AI-empowered_delivery_service_Pos	9.0%		0.000	1.000
AI-empowered_delivery_service_Neg	0.6%		0.000	1.000
Average_Observed_Score	4.347	0.213	3.400	5.000
Log(Written_Reviews)	2.326	2.094	0.000	11.703
Absence_ID_Details	74.5%		0.000	1.000
Sentiment_Polarity_Overall_Score	0.775	0.420	−0.996	1.000
Log(Review_Length)	4.304	0.658	2.890	7.431
Submission_Mobile	32.4%		0.000	1.000
Firm_Org_Structure	90.0%		0.000	1.000
Records	19,762

Table 3. Estimation results regression models – dependent variable: Overall_Experience_Score.

	Entire sample model (1)	Sample English online review model (2)
AI-empowered_delivery_service_Pos	0.412***	0.392***
	(0.0569)	(0.0596)
AI-empowered_delivery_service_Neg	−0.212	−0.222
	(0.182)	(0.191)
Average_Observed_Score	0.269*	0.263*
	(0.252)	(0.262)
Absence_ID_Details	−0.0482	−0.0363
	(0.0394)	(0.0427)
Log(Written_Reviews)	−0.113***	−0.101***
	(0.00941)	(0.0103)
Submission_Mobile	0.0493	0.0356
	(0.0354)	(0.0388)
Sentiment_Polarity_Overall_Score	2.656***	2.686***
	(0.0401)	(0.0427)
Log(Review_Length)	−0.667***	−0.690***
	(0.0253)	(0.0272)
Additional controls:
Dummy_Review_Year	YES	YES
Firm_Org_Structure	YES	YES
Firm_Category	YES	YES
Firm_Identifier	YES	YES
Intercept-1	−4.499***	−4.554***
	(1.124)	(1.169)
Intercept-2	−3.438**	−3.472**
	(1.124)	(1.168)
Intercept-3	−2.070*	−2.109*
	(1.123)	(1.168)
Intercept-4	−0.210	−0.296
	(1.123)	(1.168)
Observations	19,756	17,163
Pseudo R^2	0.182	0.178
AIC	35,747.5	31,482.1
LR Chi2	7,929.1***	6,775.9***
Log Likelihood	−17,822.8	−15,690.1

Notes: Standard errors in parentheses. The first model (1) presents fewer data points than the figure mentioned in Section 3.1 due to missing values related to the calculated Average_Observed_Score variable. * p < 0.1, ** p < 0.01, *** p < 0.001.

Table

Focal independent variable	Examples
AI-empowered_delivery_services_Neg = 1	‘During our stay [robot name] was not working, and that was disappointing.’ ‘Disappointed that the robot-powered bag storage was full when I wanted to use it.’ ‘My only regret is that we didn't get a chance to use the robots.’ ‘I was upset I never got to use [robot name]!’
AI-empowered_delivery_services_Pos = 1	‘[The hotel] is a hi-tech and modern hotel with room service robot, made me feel very excited when I saw this robot walk around the hotel.’ ‘I was pleasantly surprised, my requested additional bottled water was delivered by [robot name].’ ‘Especially loved [robot name], your robot. My daughter was excited when [robot name] got on the elevator with her. She wanted to bring [robot name] home with us!’ ‘I especially liked [robot name] the hotel’s robot butler. [Robot name] was amazingly efficient.’

Hutto, C. J., and E. Gilbert. 2014. “Vader: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text.” In Proceedings of the 8th International AAAI Conference on Weblogs and Social Media, 216–225.

 Google Scholar

Data availability statement

Data available on request from the authors.