Insights From a Text Messaging–Based Sexual and Reproductive Health Information Program in Tanzania (m4RH): Retrospective Analysis
Bibliographic record
Abstract
BACKGROUND: Many mobile health (mHealth) interventions have the potential to generate and store vast amounts of system-generated participant interaction data that could provide insight into user engagement, programmatic strengths, and areas that need improvement to maximize efficacy. However, despite the popularity of mHealth interventions, there is little documentation on how to use these data to monitor and improve programming or to evaluate impact. OBJECTIVE: This study aimed to better understand how users of the Mobile for Reproductive Health (m4RH) mHealth intervention engaged with the program in Tanzania from September 2013 to August 2016. METHODS: We conducted secondary data analysis of longitudinal data captured by system logs of participant interactions with the m4RH program from 127 districts in Tanzania from September 2013 to August 2016. Data cleaning and analysis was conducted using Stata 13. The data were examined for completeness and "correctness." No missing data was imputed; respondents with missing or incorrect values were dropped from the analyses. RESULTS: The total population for analysis included 3,673,702 queries among 409,768 unique visitors. New users represented roughly 11.15% (409,768/3,673,702) of all queries. Among all system queries for new users, 46.10% (188,904/409,768) users accessed the m4RH main menu. Among these users, 89.58% (169,218/188,904) accessed specific m4RH content on family planning, contraceptive methods, adolescent-specific and youth-specific information, and clinic locations after first accessing the m4RH main menu. The majority of these users (216,422/409,768, 52.82%) requested information on contraceptive methods; fewer users (23,236/409,768, 5.67%) requested information on clinic location. The conversion rate was highest during the first and second years of the program when nearly all users (11,246/11,470, 98.05%, and 33,551/34,830, 96.33%, respectively) who accessed m4RH continued on to query more specific content from the system. The rate of users that accessed m4RH and became active users declined slightly from 98.05% (11,246/11,470) in 2013 to 87.54% (56,696/64,765) in 2016. Overall, slightly more than one-third of all new users accessing m4RH sent queries at least once per month for 2 or more months, and 67.86% (278,088/409,768) of new and returning users requested information multiple times per month. Promotional periods were present for 15 of 36 months during the study period. CONCLUSIONS: The analysis of the rich data captured provides a useful framework with which to measure the degree and nature of user engagement utilizing routine system-generated data. It also contributes to knowledge of how users engage with text messaging (short message service)-based health promotion interventions and demonstrates how data generated on user interactions could inform improvements to the design and delivery of a service, thereby enhancing its effectiveness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.018 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".