E-mission: Automated transportation emission calculation using smartphones

Abstract

Tracking travel patterns and modes is useful on many levels. Prior efforts to collect this information have been stymied by low accuracies or reliance on supplementary devices. One technique to overcome low accuracies is to use prompted recall, in which the user is prompted to supply the ground truth for automatically generated information. However, prompted recall increases the burden on the user, which could lead to low adoption or high drop out rates. Using techniques from behavioral economics, and prompting directly on the smartphone can reduce user burden, and also increase engagement for ongoing data collection. In this paper, we describe a system that improves accuracy by using behavioral techniques for prompted recall on the smartphone, and aggregates the information to help detect large scale patterns. We also present the evaluation of a prototype implementation that was used to collect data from 44 unpaid volunteers in the San Francisco Bay Area over 3 months and compute their transportation carbon footprint.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.