PEOPLES 2018 - Second workshop on computational modeling of PEople's Opinions

On social media, users nowadays freely express what is on their mind at any moment in time, at any location, and about virtually anything. These large amounts of spontaneously produced texts open up a unique opportunity to learn more about such users, e.g., predicting demographic variables (age, gender), but also personality types, as well as emotions and opinion expressions.
Indeed, this excellent opportunity has materialized in a large and growing number of recent workshops held at different Natural Language Processing, Artificial Intelligence, Semantic Web, and Information Retrieval venues, for example WASSA (focusing on sentiment and social media), PAN (focusing on author profiling like personality) and ESSEM (focusing on emotions in AI), including the organization of shared tasks such as at SemEval with a special sentiment track.
While it is evident that interest is wide and high, it is also evident that such aspects of human personality and behavior have been mostly studied in isolation, often in different - but related - communities. We believe that the time is ripe to bring these communities a step closer, to study people’s traits and expressions jointly and in their interplay.
On a conceptual level we can view these aspects on a continuum of stability, where some can be considered stable (e.g., gender), while others are of more transitional nature and contextually prompted (e.g., emotions). They can be seen as characterizing traits of the whole person and should be studied together. As of now, however, little is known on how they interact with one another in computational language understanding, how they interact, and how they impact both natural language processing and society.
On a conceptual level we can view these aspects on a continuum of stability, where some can be considered stable (e.g., gender), while others are of more transitional nature and contextually prompted (e.g., emotions). They can be seen as characterizing traits of the whole person and should be studied together. As of now, however, little is known on how they interact with one another in computational language modeling, or how they can inform each other in modeling people or improving natural language processing tools.
We encourage the submission of long (8 pages) and short (4 pages) research papers, including opinion statements. We especially welcome views from different fields on how to treat the different aspects. We welcome submissions related but not limited to the following topics:
opinion, personality and emotion detection in social media
predicting demographic variables and author traits (gender, age, personality)
opinions, personality and emotions and their interactions
interaction between personality, opinion and emotions with demographic variables (age, gender)
interaction between personality, opinion and emotions and geo-spatial information (geographic locations and places)
interaction between personality, opinion and emotions with politics
personality, opinion and emotions and social network analysis
modeling of personality, opinion and emotions from a multimodal perspective
modeling of personality, opinion and emotions from a multilingual perspective
exploitation of the different degree of stability of the various traits
reflections on the definition of personal traits
reflection on self-selection biases and measurement biases in social media
mixed methods that combine surveys and social media analysis to study opinions, personality and emotions
applications of predictive modeling of user traits
on the ethics of predictive modeling of social variables