Supplementing a survey with respondent Twitter data to measure e-cigarette information exposure

ABSTRACT

Social media data are increasingly used by researchers to gain insights on individuals’ behaviors and opinions. Platforms like Twitter provide access to individuals’ postings, networks of friends and followers, and the content to which they are exposed. This article presents the methods and results of an exploratory study to supplement survey data with respondents’ Twitter postings, networks of Twitter friends and followers, and information to which they were exposed about e-cigarettes. Twitter use is important to consider in e-cigarette research and other topics influenced by online information sharing and exposure. Further, Twitter metadata provide direct measures of user’s friends and followers as opposed to survey self-reports. We find that Twitter metadata provide similar information to survey questions on Twitter network size without inducing recall error or other measurement issues. Using sentiment coding and machine learning methods, we find Twitter can elucidate on topics difficult to measure via surveys such as online expressed opinions and network composition. We present and discuss models predicting whether respondents’ tweet positively about e-cigarettes using survey and Twitter data, finding the combined data to provide broader measures than either source alone.     

Online measures of looking and learning in infancy

Infants in laboratory settings look longer at events that violate their expectations, learn better about objects that behave unexpectedly, and match utterances to the objects that likely elicited them. The paradigms revealing these behaviors have become cornerstones of research on preverbal cognition. However, little is known about whether these canonical behaviors are observed outside laboratory settings. Here, we describe a series of online protocols that replicate classic laboratory findings, detailing our methods throughout. In Experiment 1a, 15-month-old infants (N = 24) looked longer at an online support event culminating in an Unexpected outcome (i.e., appearing to defy gravity) than an Expected outcome. Infants did not, however, show the same success with an online solidity event. In Experiment 1b, 15-month-old infants (N = 24) showed surprise-induced learning following online events—they were better able to learn a novel object's label when the object had behaved unexpectedly compared to when it behaved expectedly. Finally, in Experiment 2, 16-month-old infants (N = 20) who heard a valenced utterance (“Yum!”) showed preferential looking to the object most likely to have generated that utterance. Together, these results suggest that, with some adjustments, online testing is a feasible and promising approach for infant cognition research.     

International cooperation in stockpiles and tariffs for coping with oil supply disruptions

This paper provides a unified treatment of oil stockpiling and demand restraint as policy responses for enhancing energy security and examines the implications of recent changes in the structure and performance of the international oil market for the design of policies. These issues are addressed using a dynamic programming framework in which international policy actions of key oil-importing countries are modeled as a Nash dynamic game. Significant policy implications from the analysis include: (1) the result that, with realistic assumptions about disruption risks and inventory capacities, differences between noncooperative and coordinated stockpile policies appear to be minor and (2) significant mutual gains could be reaped from a modest degree of collective restraint on normal market oil demand. The broader role of international cooperation in enhancing energy security is also discussed.     

Family and sociodemographic influences on patterns of leaving home in Postwar Britain

We identify child-level and parent-level characteristics associated with children’s patterns of leaving home. We use a multilevel discrete-time hazards model to examine the impact of family and demographic factors at both levels, and utilize the Alternating Conditional Expectation algorithm optimally to transform the dependent and independent variables. We find that measured variables at both the child and the parent level have important influences, as do period and cohort factors. However, unmeasured parent-level factors have an influence on the departure of children that is broadly similar in magnitude to measured factors.     

Mixture of latent trait analyzers for model-based clustering of categorical data

Model-based clustering methods for continuous data are well established and commonly used in a wide range of applications. However, model-based clustering methods for categorical data are less standard. Latent class analysis is a commonly used method for model-based clustering of binary data and/or categorical data, but due to an assumed local independence structure there may not be a correspondence between the estimated latent classes and groups in the population of interest. The mixture of latent trait analyzers model extends latent class analysis by assuming a model for the categorical response variables that depends on both a categorical latent class and a continuous latent trait variable; the discrete latent class accommodates group structure and the continuous latent trait accommodates dependence within these groups. Fitting the mixture of latent trait analyzers model is potentially difficult because the likelihood function involves an integral that cannot be evaluated analytically. We develop a variational approach for fitting the mixture of latent trait models and this provides an efficient model fitting strategy. The mixture of latent trait analyzers model is demonstrated on the analysis of data from the National Long Term Care Survey (NLTCS) and voting in the U.S. Congress. The model is shown to yield intuitive clustering results and it gives a much better fit than either latent class analysis or latent trait analysis alone.     

Assessing outcomes in an English authority (The Royal Borough of Kensington and Chelsea)

The local authority has used the Looking After Children materials to develop needs-led and outcome-oriented services at both individual and strategic planning levels. A specific study used data from the Assessment and Action Records to identify priority needs and desired outcomes for young people leaving care.