2019.04 Paper Weekly 2
-
- Motivation: Daily commuting time increasing
- Research Gap: how contextual targeting with commuting impacts user redemptions of mobile coupons
- Method: field study
- Finding:
- commuters are about 3× as likely to redeem their mobile coupon compared with noncommuters
- a multiple-coupon distribution strategy is more effective in increasing redemption among noncommuters than commuters
- the redemption rate of commuters is higher for coupons with shorter expiration periods, whereas that of noncommuters is higher for coupons with longer expiration periods.
- Theory:
- stress, which is exacerbated by commuting, increases commuters’ coupon redemption rate.
-
- Motivation: Peer review is cornerstone of academic practice
- Research goal: identify opportunities and describe a few early solutions fro automating key stages in the established academic peer review process
- Writing: 当有很多文章，你仍想在这一块做类似贡献 -> Yet, despite many publications on this topic over the intervening years, research results in paper assignment have made relatively few inroads into mainstream CMS tools and everyday peer review practice. Hence, whagt we have achieved over the last 25 years or so appears to be a streamlined process rather than a fundamentally improved one: we believe it would be difficult to argue the decisions taken by program committees today are significantly better in comparison with the paper-based process. But this doesn’t mean that opportunities for imroving the process don’t exist-on the contrary, there is, as we demonstrate in this article, considerable scope for exploying the very techniques that researc hers in machine learning and artificial intelligence have been developing over the years.
-
- Motivation: Social media analytics require geolocation data.
- 当我觉得Twitter内部可以依靠IP地址来获知地理位置的时候，作者给出了适当的解释。the percentage of geotagged tweets is low and Twitter user profile location data is often unreliable.
- Proposed method: a novel statistical approach for country-level location detection of Twitter users.
- The proposed Google Trends nouns (GTN) method uses GT to solve a spatial detection task rather than a temporal task (as proposed in previous GT studies).
- Motivation: Social media analytics require geolocation data.
-
Modeling individuals’ willingness to share trips with strangers in an autonomous vehicle future
- Motivation: Autonomous Vehicles
- Research gap: willingness to sharing the same AV
- Findings:
- users are less sensitive to the presence of strangers when in a commute trip compared to a leisure-activity trip.
- the travel time added to the trip to serve other passengers may be a greater barrier to the use of shared services compared to the presence of a stranger
-
- Motivation: internet
- Research gap: whether these platforms truly alleviate the influence of geographic distance remains unexplored
- Findings: not only the geographic distance and network ties exhibit an inverse association but also that geographic distance is the strongest predictor of such ties.
-
Deep Reinforcement Learning with Applications in Transportation
- Question:
- Ride-sharing Platform
- Order dispatching
- Driver repositioning
- Drivers distribution
- Micro-level Impact
- Short-term
- Long-term
- Carpool
- Multiple passengers
- Factors to consider
- Route Planning
- Planning a route for a trip on map
- Planning a route for robot navigation
- Traffic Signals Control
- Ride-sharing Platform
- Question: