Characterising and Mitigating Aggregation-Bias in Crowdsourced Toxicity Annotations

Training machine learning (ML) models for natural language processing usually requires large amount of data, often acquired through crowdsourcing. The way this data is collected and aggregated can have an effect on the outputs of the trained model such as ignoring the labels which differ from the majority. In this paper we investigate how label...

A Human in the Loop Approach to Capture Bias and Support Media Scientists in News Video Analysis

Bias is inevitable and inherent in any form of communication. News often appear biased to citizens with dierent political orientations, and understood dierently by news media scholars and the broader public. In this paper we advocate the need for accurate methods for bias identication in video news item, to enable rich analytics capabilities in...

A user modeling pipeline for studying polarized political events in social media

This paper presents a user modeling pipeline to analyze discussions and opinions shared on social media regarding polarized political events (e.g., public polls). The pipeline follows a four-step methodology. First, social media posts and users metadata are crawled. Second, a filtering mechanism is applied to filter spammers and bot users. As a...

Effective crowdsourced generation of training data for chatbots natural language understanding

Chatbots are text-based conversational agents. Natural Language Understanding (NLU) models are used to extract meaning and intention from user messages sent to chatbots. The user experience of chatbots largely depends on the performance of the NLU model, which itself largely depends on the initial dataset the model is trained with. The training...

TSE-NER: An Iterative Approach for Long-Tail Entity Extraction in Scientific Publications

Named Entity Recognition and Typing (NER/NET) is a challenging task, especially with long-tail entities such as the ones found in scientific publications. These entities (e.g. “WebKB”, “StatSnowball”) are rare, often relevant only in specific knowledge domains, yet important for retrieval and exploration purposes. State-of-the-art NER approaches...

Concept Focus: Semantic Meta-Data For Describing MOOC Content

MOOCs promised to herald a new age of open education.<br/>However, efficient access to MOOC content is still hard, thus unneces-<br/>sarily complicating many use cases like efficient re-use of material, or<br/>tailored access for life-long learning scenarios. One of the reasons for this<br/>lack of accessibility is the shortage of meaningful...

CitRec 2017: International Workshop on Recommender Systems for Citizens

The "International Workshop on Recommender Systems for Citizens" (CitRec) is focused on a novel type of recommender systems both in terms of ownership and purpose: recommender systems run by citizens and serving society as a whole.

MRLR: Multi-level representation learning for personalized ranking in recommendation

Representation learning (RL) has recently proven to be effective in capturing local item relationships by modeling item co-occurrence in individual user's interaction record. However, the value of RL for recommendation has not reached the full potential due to two major drawbacks: 1) recommendation is modeled as a rating prediction problem...

Recommender systems for citizens: The CitRec'17 workshop manifesto

This manifesto summarises the outcomes of the 1st Workshop on Recommender Systems for Citizens (CitRec'17), held at the 11th ACM Conference on Recommender Systems, in August 2017 in Como, Italy. We discuss challenges and opportunities for the development of recommender systems for citizens, including: the clarification of the role of recommender...

Social media data analytics for tourism: A preliminary study

Social media data are increasingly used as the source of research in a variety of domains. A typical example is urban analytics, which aims at solving urban problems by analyzing data from different sources including social media. The potential value of social media data in tourism studies, which is one of the key topics in urban research,...

On the Improvement of Quality and Reliability of Trust Cues in Micro-task Crowdsourcing

Micro-task crowdsourcing has become a successful mean to obtain high-quality data from a large crowd of diverse people. In this context, trust between all the involved actors (i.e. requesters, workers, and platform owners) is a critical factor for acceptance and long-term success. As actors have no expectation for “real life” meetings, thus...

Harnessing heterogeneous social data to explore, monitor, and visualize urban dynamics

Understanding the complexity of urban dynamics requires the combination of information from multiple city data sources. Besides traditional urban data, geo-localized social media provide human-generated content, which may reflect in (near) real time the activities people undertake in cities. The challenge is to devise methods and tools that...

From Needs to Knowledge: A reference framework for smart citizens initiatives

Citizens are a fundamental component for the success of the smart cities vision. The actor-observant duality of people in urban environments is one of the key arguments of the smart cities debate: how can citizens be empowered in the detection, analysis, and solution of modern urban challenges? How can public authorities support collective...

Asking the right question in collaborative O&A systems

Collaborative Question Answering (cQA) platforms are a very popular repository of crowd-generated knowledge. By formulating questions, users express needs that other members of the cQA community try to collaboratively satisfy. Poorly formulated questions are less likely to receive useful responses, thus hindering the overall knowledge generation...

Platform for Task Recommendation in Human Computation

Crowdsourcing and Human computation have enabled industry and<br/>scientists to create innovative solutions by harnessing organised<br/>collective human effort. In human computation platforms, it is<br/>observed that workers spend large amount of time searching for<br/>appropriate tasks due to lack of effective task discovery mechanism. This...

Towards a top-K SPARQL query benchmark generator

The research on optimization of top-k SPARQL query would largely benefit from the establishment of a benchmark that allows comparing different approaches. For such a benchmark to be meaningful, at least two requirements should hold: 1) the benchmark should resemble reality as much as possible, and 2) it should stress the features of the topk...

Towards a top-K SPARQL query benchmark generator

The research on optimization of top-k SPARQL query would largely benefit from the establishment of a benchmark that allows comparing different approaches. For such a benchmark to be meaningful, at least two requirements should hold: 1) the benchmark should resemble reality as much as possible, and 2) it should stress the features of the topk...