Abstract“Lifestyle politics” suggests that political and ideological opinions are strongly connected to our consumption choices, music and food taste, cultural preferences, and other aspects of our daily lives. With the growing political polarization this idea has become all the more relevant to a wide range of social scientists. Empirical research in this domain, however, is confronted with an impractical challenge; this type of detailed information on people’s lifestyle is very difficult to operationalize, and extremely time consuming and costly to query in a survey. A potential valuable alternative data source to capture these values and lifestyle choices is social media data. In this study, we explore the value of Facebook “like” data to complement traditional survey data to study lifestyle politics. We collect a unique dataset of Facebook likes and survey data of more than 6500 participants in Belgium, a fragmented multi-party system. Based on both types of data, we infer the political and ideological preference of our respondents. The results indicate that non-political Facebook likes are indicative of political preference and are useful to describe voters in terms of common interests, cultural preferences, and lifestyle features. This shows that social media data can be a valuable complement to traditional survey data to study lifestyle politics.

Increasing levels of political animosity in the United States invite speculation about whether polarization extends to aspects of daily life. However, empirical study about the relationship between political ideologies and lifestyle choices is limited by a lack of comprehensive data. In this research, we combine survey and Facebook Page "likes" data from more than 1,200 respondents to investigate the extent of polarization in lifestyle domains. Our results indicate that polarization is present in page categories that are somewhat related to politics -such as opinion leaders, partisan news sources, and topics related to identity and religion -but, perhaps surprisingly, it is mostly not evident in other domains, including sports, food, and music. On the individual level, we find that people who are higher in political news interest and have stronger ideological predispositions have a greater tendency to "like" ideologically homogeneous pages across categories. Our evidence, drawn from rare digital trace data covering more than 5,000 pages, adds nuance to the narrative of widespread polarization across lifestyle sectors and it suggests domains in which cross-cutting preferences are still observed in American life.

Studies have shown that parties selectively emphasize different issues to compete with each other to raise the salience for their preferred issues and to appear competent in handling them. This study applies the selective emphasis framework on individual politicians. We argue that politicians compete with both politicians from different parties as with their party members. We expect that issue ownership matters to compete with politicians from different parties and issue specialization to compete with politicians from their own party. We studied the individual issue agenda of 144 Belgian politicians for a period of 9 months on Twitter, in the news and in parliament. Our results show that issue specialization is a consistent driver of the three issue agendas of politicians, while the effect of issue ownership varies across agendas. This means that both factors are not mutually exclusive and that combining them can be an opportune strategy for politicians.

An important aspect of the growing e-commerce sector involves the delivery of tangible goods to the end customer, the so-called last mile. This final stage of the logistics chain remains highly inefficient due to the problem of failed deliveries. To address this problem, delivery service providers can apply data science to determine the optimal, customercentered location and time window for handover. In this article, we present a three-step approach for location prediction, based on mobile location data, in order to support delivery planning. The first step is identifying a user's locations of interest through density-based clustering. Next, the semantics (home or work) of the user's locations of interest are discovered, based on temporal assumptions. Finally, we predict future locations with a decision tree model that is trained on each user's historical location data. Though the problem of location prediction is not new, this work is the first to apply it to the field of parcel delivery with its corresponding implications. Moreover, we provide a novel and detailed evaluation on real-world data from a parcel delivery service. The promising results indicate that our approach has the potential to help delivery service providers to gain insights into their customers' optimal delivery time and location in order to support delivery planning. Eventually this will decrease last-mile delivery costs and boost customer satisfaction. [