scholarly journals Working Paper: Application of automatic sentiment analysis: The role of emotions in an experimental learning intervention

2020 ◽  
Author(s):  
Manyu Li

This secondary-analysis register report aims at testing the role of emotion in the intervention effect of an experimental intervention study in academic settings. Previous analyses of the National Study of the Learning Mindset (Yeager et al., 2019) showed that in a randomized controlled trial, high school students who were given the growth mindset intervention had, on average higher GPA than did students in the control condition. Previous analyses also showed that school achievement levels moderated the intervention effect. This study further explores whether the emotion students experienced during the growth mindset intervention plays a role in the intervention effect. Specifically, using a sentence-level automated text analysis for emotional valence (i.e. sentiment analysis), students’ written reflections during the intervention are analyzed. Linear mixed models are conducted to test if valence reflected in the written texts predicted higher intervention effect (i.e. higher post-intervention GPA given pre-intervention GPA). The moderating role of school achievement levels was also examined. A 10% random sample of the data was analyzed as a pilot study for this registered report to test for feasibility and proof-of-concept. Results of the pilot data showed small, yet significant relations between emotional valence and intervention effects. The results of this study have implications on the role of emotion in the results of intervention or experimental studies, especially those that are conducted in academic settings. This study also introduces a user-friendly text-based analytic method for experimental psychologists to detect and analyze sentence-level emotional valence in an intervention or experimental study.

2020 ◽  
Author(s):  
Soobin Kim ◽  
Barbara Schneider ◽  
John Yun

Using a randomized controlled trial in a nationally representative sample of 65 public high schools (N = 13,660), we tested the effects of a growth mindset intervention on math course- taking patterns and student achievement and explored whether school context was related to the success of the intervention. Students were randomly assigned to complete either the growth mindset intervention or a control activity during two 25-minute sessions. After participating in the growth mindset program used in the National Study of Learning Mindsets, students’ 9th- grade mathematics GPA increased by an average of 0.05 grade points on a 4.3-point scale. We found distinct patterns of treatment effects that depend on level of math preparation, course intensity, school context, and changes in students’ mindset.


2020 ◽  
Vol 42 (6) ◽  
pp. 460-468 ◽  
Author(s):  
Caitlin Brez ◽  
Eric M. Hampton ◽  
Linda Behrendt ◽  
Liz Brown ◽  
Josh Powers

2018 ◽  
Vol 38 (6) ◽  
pp. 711-733 ◽  
Author(s):  
Teresa K. DeBacker ◽  
Benjamin C. Heddy ◽  
Julianna Lopez Kershen ◽  
H. Michael Crowson ◽  
Kristyna Looney ◽  
...  

2019 ◽  
Author(s):  
Vasundhara Sridharan ◽  
Yuichi Shoda ◽  
Jaimee Heffner ◽  
Jonathan Bricker

BACKGROUND Although smartphone apps have shown promise for smoking cessation, there is a need to enhance their low engagement rates. This study evaluated the application of the growth mindset theory, which has demonstrated the potential to improve persistence in behavior change in other domains, as a means to improve engagement and cessation. OBJECTIVE This study aimed to explore the feasibility, utility, and efficacy of a Web-based growth mindset intervention for addiction when used alongside a smoking cessation app. METHODS Daily smokers (N=398) were all recruited on the Web and randomly assigned to receive either a cessation app alone or the app plus a Web-delivered growth mindset intervention. The primary outcome was engagement, that is, the number of log-ins to the smoking cessation app. The secondary outcome was 30-day point prevalence abstinence at 2-month follow-up collected through a Web-based survey. RESULTS The 2-month outcome data retention rate was 91.5% (364/398). In addition, 77.9% (310/398) of the participants in the experimental arm viewed at least 1 page of their growth mindset intervention, and 21.1% (84/398) of the group viewed all the growth mindset intervention. The intention-to-treat analysis did not show statistically significant differences between the experimental and comparison arms on log-ins to the app (19.46 vs 21.61; P=.38). The experimental arm had cessation rates, which trended higher than the comparison arm (17% vs 13%; P=.10). The modified intent-to-treat analysis, including only participants who used their assigned intervention at least once (n=115 in experimental group and n=151 in the control group), showed that the experimental arm had a similar number of log-ins (32.31 vs 28.48; P=.55) but significantly higher cessation rates (21% vs 13%; P=.03) than the comparison arm. CONCLUSIONS A growth mindset intervention for addiction did not increase engagement rates, although it may increase cessation rates when used alongside a smartphone app for smoking cessation. Future research is required to refine the intervention and assess efficacy with long-term follow-up to evaluate the efficacy of the mindset intervention. CLINICALTRIAL ClinicalTrials.gov NCT03174730; https://clinicaltrials.gov/ct2/show/NCT03174730


Sign in / Sign up

Export Citation Format

Share Document