Voting Advice Applications (VAAs) are Web tools that are used to inform increasing numbers of voters during elections. This increasing usage indicates that VAAs fulfill voters' needs, but what these needs are is unknown. Previous research has shown that such tools are primarily used by young males and highly educated citizens. This suggests that VAAs are generally used by citizens who are already well-informed about politics and may not need the assistance of a VAA to make voting decisions. To analyze the functions that VAAs have for their users, this study utilizes unique user data from a popular Dutch VAA to identify different user types according to their cognitive characteristics and motivations. A latent class analysis (LCA) resulted in three distinct user types that vary in efficacy, vote certainty, and interest: doubters, checkers, and seekers. Each group uses the VAA for different reasons at different points in time. Seekers' use of VAAs increases as Election Day approaches; less efficacious and less certain voters are more likely to use the tool to become informed.

Survey designers have long assumed that respondents who disagree with a negative question ("This policy is bad.": Yes or No; 2-point scale) will agree with an equivalent positive question ("This policy is good.": Yes or No; 2-point scale). However, experimental evidence has proven otherwise: Respondents are more likely to disagree with negative questions than to agree with positive ones. To explain these response effects for contrastive questions, the cognitive processes underlying question answering were examined. Using eye tracking, the authors show that the first reading of the question and the answers takes the same amount of time for contrastive questions. This suggests that the wording effect does not arise in the cognitive stages of question comprehension and attitude retrieval. Rereading a question and its answering options also takes the same amount of time, but happens more often for negative questions. This effect is likely to indicate a mapping difference: Fitting an opinion to the response options is more difficult for negative questions.

In this paper, we focus on data-driven approaches to human activity recognition (HAR). Data-driven approaches rely on good quality data during training, however, a shortage of high quality, large-scale, and accurately annotated HAR datasets exists for recognizing activities of daily living (ADLs) within smart environments. The contributions of this paper involve improving the quality of an openly available HAR dataset for the purpose of data-driven HAR and proposing a new ensemble of neural networks as a data-driven HAR classifier. Specifically, we propose a homogeneous ensemble neural network approach for the purpose of recognizing activities of daily living within a smart home setting. Four base models were generated and integrated using a support function fusion method which involved computing an output decision score for each base classifier. The contribution of this work also involved exploring several approaches to resolving conflicts between the base models. Experimental results demonstrated that distributing data at a class level greatly reduces the number of conflicts that occur between the base models, leading to an increased performance prior to the application of conflict resolution techniques. Overall, the best HAR performance of 80.39% was achieved through distributing data at a class level in conjunction with a conflict resolution approach, which involved calculating the difference between the highest and second highest predictions per conflicting model and awarding the final decision to the model with the highest differential value.

In many countries with multiparty systems, a decline in class voting has increased volatility and the need for comprehensive information about the political landscape among voters. Voting Advice Applications (VAAs) are online tools that match users to political parties and, as such, they hold a promise of reinforcing informational transparency and democratic representation. The current research investigated whether VAAs live up to this expectation by investigating to what extent VAAs affected users' political knowledge and vote choice in the Dutch national elections of 2012. Results show that VAA users feel that the VAA improved their political knowledge. In addition, those groups of VAA users who experienced a large knowledge increase, also relatively often indicated that their vote choice had been affected. This suggests that VAAs contribute to informational transparency by increasing knowledge among a potentially wide audience, and also that VAAs might increase democratic representation to the extent that VAAs persuade people to vote for the candidate that best represents their opinions. On the other hand, we found discrepancies between behavioural and perceptual measurements of the effect of VAAs on vote choice. This raises doubts about whether VAAs shape actual voting behaviours and knowledge, or rather perceptions of that.

No abstract

Online Voting Advice Applications (VAAs) are survey-like instruments that help citizens to shape their political preferences and compare them with those of political parties. Especially in multi-party democracies, their increasing popularity indicates that VAAs play an important role in opinion formation for citizens, as well as in the public debate prior to elections. Hence, the objectivity and transparency of VAAs are crucial. In the design of VAAs, many choices have to be made. Extant research in survey methodology shows that the seemingly arbitrary choice to word questions positively (e.g., ‘The city council should allow cars into the city centre’) or negatively (‘The city council should ban cars from the city centre’) systematically affects the answers. This asymmetry in answers is in line with work on negativity bias in other areas of linguistics and psychology. Building on these findings, this study investigated whether question polarity also affects the answers to VAA statements. In a field experiment (N = 31,112) during the Dutch municipal elections we analysed the effects of polarity for 16 out of 30 VAA statements with a large variety of linguistic contrasts. Analyses show a significant effect of question wording for questions containing a wide range of implicit negations (such as ‘forbid’ vs. ‘allow’), as well as for questions with explicit negations (e.g., ‘not’). These effects of question polarity are found especially for VAA users with lower levels of political sophistication. As these citizens are an important target group for Voting Advice Applications, this stresses the need for VAA builders to be sensitive to wording choices when designing VAAs. This study is the first to show such consistent wording effects not only for political attitude questions with implicit negations in VAAs, but also for political questions containing explicit negations.

Data driven approaches for human activity recognition learn from pre-existent large-scale datasets to generate a classification algorithm that can recognize target activities. Typically, several activities are represented within such datasets, characterized by multiple features that are computed from sensor devices. Often, some features are found to be more relevant to particular activities, which can lead to the classification algorithm providing less accuracy in detecting the activity where such features are not so relevant. This work presents an experimentation for human activity recognition with features derived from the acceleration data of a wearable device. Specifically, this work analyzes which features are most relevant for each activity and furthermore investigates which classifier provides the best accuracy with those features. The results obtained indicate that the best classifier is the k-nearest neighbor and furthermore, confirms that there do exist redundant features that generally introduce noise into the classification, leading to decreased accuracy.

Sensor-based activity recognition involves the automatic recognition of a user's activity in a smart environment using computational methods. The use of wearable devices and video-based approaches have attracted considerable interest in ubiquitous computing. Nevertheless, these methods have limitations such as issues with privacy invasion, ethics, comfort and obtrusiveness. Environmental sensors are an increasingly promising consideration in the ubiquitous computing domain for long-term monitoring, as these devices are non-invasive to inhabitants, yet certain challenges remain with activity recognition in sensorised environments, for example, addressing the challenge of intraclass variation between activities and reasoning from low-level uncertain information. In an effort to address these challenges, this paper proposes and evaluates the performance of a Radial Basis Function Neural Network approach for activity recognition with environmental sensors. The model is trained using the Localized Generalization Error and focuses on the generalization ability by considering both the training error and stochastic sensitivity measure. This measures the network output fluctuation with respect to the minor perturbation of input, to address the tolerance of the low-level uncertain sensor data. This approach is compared with three benchmark Neural Network approaches, including a popular deep learning approach using an Autoencoder, and it is evaluated with a simulated dataset as well as a number of publicly available datasets. The proposed method has shown advantages over the other models for all four evaluated datasets. This paper provides insights into the importance of model generalization abilities and an initial analysis of the limitation of deep Neural Networks with respect to sensor-based activity recognition.