Browsing by Author "De Renzi, Brian"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    The effects of monetary and non-monetary incentives on respondent attrition in longitudinal survey
    (2019) Choga, Ngonidzashe Nicholas; De Renzi, Brian; Rosenstock, Todd
    Longitudinal studies are essential for governments and organizations as they help in making decisions that are based on factual data. Longitudinal studies collect data repeatedly from a set of participants over a period of time, enabling the tracking and studying of entity behaviour at individual, organizational, and national levels. One major challenge facing longitudinal data collection is the attrition of subjects during the course of the study, which is the continuous loss of participants during a longitudinal survey due to verbal drop-outs and non-response. Attrition can render datasets useless due to incomplete entries, making it one of the most significant weaknesses of longitudinal surveys. In order to explore the effects of incentives on attrition, this research project studies the effects of monetary and non-monetary incentives on explicit (subject says s/he does not want to be part of the study) and implicit (non-response) attrition. In particular, this study uses telephonically delivered feedback, derived from participant responses, as non-monetary incentives. To measure the effects of incentives on attrition, the study gave four treatments groups —50 participants each—mobile credit, verbally delivered feedback, machine delivered feedback and no incentive. After monitoring their attrition, over a 12-week period that involved bi-weekly surveys, a generalised linear model and Cochran’s q-test were used to find that monetary incentives remain the strongest in under-served community settings. It was not only found that monetary incentive treatments completed the most surveys most weeks, but also had the least explicit attrition. Surprisingly it was also found that machine delivered feedback performed similarly to mobile credit when the cost, social impact and participant behaviour in terms of their survey completion and attrition is assessed.
  • Thumbnail Image
    Item
    Open Access
    Using question-specific vocabularies to support speech data collection with SALAAM
    (2019) Chibuye, Kayokwa Nick; De Renzi, Brian
    There has been an increasing use of small-vocabulary spoken dialogue systems in low-resource settings for information dissemination and data collection. This provides an opportunity to reduce the information gap in low-resource settings in which low-literacy is a huge hindrance to the adoption of Information Communication Technologies (ICTs). Since the languages spoken in these areas are computationally low-resourced, they rely on techniques such as crosslanguage phoneme mapping to facilitate fast development of small-vocabulary speech recognisers. Despite the success of this technique, there has been a lack of guidance on how to deploy such systems across a range of languages. This study presents a systematic exploration of the suitability and limitations of using crosslanguage phoneme mapping for the development of small-vocabulary speech recognisers for computationally low-resource languages, particularly Bantu languages. Five target languages and four source languages were used in the study. Speech-based Accent Learning And Articulation Mapping (SALAAM), a cross-language phoneme mapping algorithm was used to aid the study based on its implementation in an open-source tool Lex4All. The following research questions guided our investigations: i) What impact does source language choice have on recognition accuracy, ii) What impact does gender composition of the training data set have on recognition accuracy and iii) What impact do varied alternative pronunciations per word type have on recognition accuracy. Data for the target languages was collected from 104 university student volunteers consisting of 58 female and 46 male students. The results showed that target and source language phonetic similarity as well as gender composition of the training datasets affects recognition accuracy of speech applications developed using cross-language phoneme mapping techniques. They also showed that increasing the number of alternative pronunciations per word in the vocabulary generally increases recognition accuracy although with a slower system response time. This study provides evidence that a careful selection of the source language, gender composition of the training data and the number of alternative pronunciations per word can improve the recognition accuracy of speech recognisers developed using cross-language phoneme mapping.