Approaching positive objects and avoiding negative ones are general action tendencies in human behavior. Interestingly, hand or arm positions connoting approach (arm flexion) or avoidance (arm extension) have also been shown to influence how the valence of a stimulus is evaluated. However, this causal effect on valence evaluation has been typically examined within experimental paradigms that do not require acting upon objects such as when touching or moving them. Accordingly, the current study attempts to integrate approach–avoidance paradigms with findings suggesting that manipulating visual stimuli directly by hand modulates their cognitive processing. Sixty participants evaluated the valence of 40 emotional pictures from the International Affective Picture System (IAPS) twice, first after watching them on a monitor (i.e., baseline evaluations) and second after swiping them on a touchscreen, either toward or away from their body (i.e., interactions regulating distance). Our findings confirmed that, in contrast to just watching the pictures, (a) swiping positive pictures closer and negative pictures away led to positively change their valence evaluation (i.e., reinforcing the perceived valence of positive pictures and attenuating the perceived valence of negative pictures). However, (b) swiping negative pictures closer and positive pictures away barely changed their initial valence evaluation. Against this background, we argue that swiping emotional pictures closer or away directly by hand, may intensify the attentional prioritization to interactions leading to more desirable consequences, namely, approaching positive and avoiding negative stimuli.
Text classification is important to better understand online media. A major problem for creating accurate text classifiers using machine learning is small training sets due to the cost of annotating them. On this basis, we investigated how SVM and NBSVM text classifiers should be designed to achieve high accuracy and how the training sets should be sized to efficiently use annotation labor. We used a four-way repeated-measures full-factorial design of 32 design factor combinations. For each design factor combination 22 training set sizes were examined. These training sets were subsets of seven public text datasets. We study the statistical variance of accuracy estimates by randomly drawing new training sets, resulting in accuracy estimates for 98,560 different experimental runs. Our major contribution is a set of empirically evaluated guidelines for creating online media text classifiers using small training sets. We recommend uni- and bi-gram features as text representation, btc term weighting and a linear-kernel NBSVM. Our results suggest that high classification accuracy can be achieved using a manually annotated dataset of only 300 examples.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.