Participant Engagement with a Hyper-Personalized Activity Tracking Smartphone App
Notice bibliographique
Résumé
Background: Many mobile apps have been designed to monitor physical activity. While they may have many downloads, most users eventually stop using the app and become disengaged. We created a hyper-personalized physical activity tracking app to promote engagement with physical activity (PA) among users. It is unknown if this increased engagement and how engagement level may affect measured outcomes. Objective: The purpose of this study was to determine how users engaged with a hyper personalized activity tracking app for 6 months and whether this engagement affected physical activity Methods: Participants with cardiometabolic risk (CMR) factors were given an activity watch to track their PA (step counts) and asked to use the study mobile app for 6 months. App features included step tracking, personalized educational and motivational messages, biometric tracking and connection to a portal where their clinician could monitor their activity. App usage data were collected at 3- and 6-month study visits to determine app usage metrics for the 6 months. App engagement was determined by app usage metrics such as overall page clicks (number of clicks per page), frequency of use of individual features (number of clicks) and session length (time spent on a page). Participants were grouped by level of engagement with app (high, medium, low, none) post hoc to determine engagement effects on steps. Results: Information was collected on 128 participants. Over the 6-month study, 60 participants (47%) engaged with the app. Among users, app usage decreased by over 50% with the highest app usage during month 1 followed by month 4. There was no difference in the average app session lengths at 0 and 6 months (12 vs 11 seconds, respectively). The most commonly viewed feature was the personalized daily messages (92% of participants used feature, 20,902 clicks, 58% of total views). At least 85% of app users engaged with all the features. Each additional day of app use was associated with a nonsignificant increase of 13 steps in overall average daily step count. Median days of app use were used to define groups with high, medium, and low engagement (median 89, 35 and 3 days of use respectively). The low engagement group had an average 1220 less steps per day than the high engagement group (P<.001). High engagement group’s session length remained steady through the study period, compared to medium engagement group’s session length that fluctuated widely. While steps decreased over the 6 months, those in the medium engagement group decreased in weekly step counts at a steeper slope then other engagement groups. Conclusions: While participants engaged with most app features, we observed a 50% decrease in engagement over the 6-month study. Despite this result, those with high engagement were able to achieve more physical activity than those with low engagement. This increase in physical activity may lead to improvements in CMR factors and better quality of life.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,002 | 0,007 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,000 | 0,000 |
| Bibliométrie | 0,000 | 0,000 |
| Études des sciences et des technologies | 0,001 | 0,000 |
| Communication savante | 0,001 | 0,000 |
| Science ouverte | 0,000 | 0,001 |
| Intégrité de la recherche | 0,000 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,007 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».