In a modern recommender system, it is important to understand how products relate to each other. For example, while a user is looking for mobile phones, it might make sense to recommend other phones, but once they buy a phone, we might instead want to recommend batteries, cases, or chargers. These two types of recommendations are referred to as substitutes and complements: substitutes are products that can be purchased instead of each other, while complements are products that can be purchased in addition to each other.Here we develop a method to infer networks of substitutable and complementary products. We formulate this as a supervised link prediction task, where we learn the semantics of substitutes and complements from data associated with products. The primary source of data we use is the text of product reviews, though our method also makes use of features such as ratings, specifications, prices, and brands. Methodologically, we build topic models that are trained to automatically discover topics from text that are successful at predicting and explaining such relationships. Experimentally, we evaluate our system on the Amazon product catalog, a large dataset consisting of 9 million products, 237 million links, and 144 million reviews.

The recent surge in women reporting sexual assault and harassment (e.g., #metoo campaign) has highlighted a longstanding societal crisis. This injustice is partly due to a culture of discrediting women who report such crimes and also, rape myths (e.g., 'women lie about rape'). Social web can facilitate the further proliferation of deceptive beliefs and culture of rape myths through intentional messaging by malicious actors.This multidisciplinary study investigates Twitter posts related to sexual assaults and rape myths for characterizing the types of malicious intent, which leads to the beliefs on discrediting women and rape myths. Specifically, we first propose a novel malicious intent typology for social media using the guidance of social construction theory from policy literature that includes Accusational, Validational, or Sensational intent categories. We then present and evaluate a malicious intent classification model for a Twitter post using semantic features of the intent senses learned with the help of convolutional neural networks. Lastly, we analyze a Twitter dataset of four months using the intent classification model to study narrative contexts in which malicious intents are expressed and discuss their implications for gender violence policy design.

Social media has become an alternative communication mechanism for the public to reach out to emergency services during time-sensitive events. However, the information overload of social media experienced by these services, coupled with their limited human resources, challenges them to timely identify, prioritize, and organize critical requests for help. In this paper, we first present a formal model of serviceability called Social-EOC, which describes the elements of a serviceable message posted in social media expressing a request. Using the serviceability model, we then describe a system for the discovery and ranking of highly serviceable requests as well as for re-ranking requests by semantic grouping to reduce redundancy and facilitate the browsing of requests by responders. We validate the model for emergency services by experimenting with six crisis event datasets and ground truth provided by emergency professionals. Our experiments demonstrate that features based on both serviceability model and social connectedness improve the performance of discovering and ranking (nDCG gain up to 25%) service requests over different baselines. We also empirically validate the existence of redundancy and semantic coherence among the serviceable requests using our semantic grouping approach, which shows the significance and need for grouping similar requests to save the time of emergency services. Thus, an application of serviceability model could reduce cognitive load on emergency servicers in filtering, ranking, and organizing public requests on social media at scale.

No abstract

No abstract