Jens Grivolla

Urban cycles and mobility patterns: Exploring and predicting trends in a bicycle-based public transport system

This paper provides an analysis of human mobility data in an urban area using the amount of available bikes in the stations of the community bicycle program Bicing in Barcelona. Based on data sampled from the operators website, it is possible to detect temporal and geographic mobility patterns within the city. These patterns are applied to predict the number of available bikes for any station some minutes/hours ahead. The predictions could be used to improve the bicycle program and the information given to the users via the Bicing website.

A Hybrid Recommender Combining User, Item and Interaction Data

While collaborative filtering often yields very good recommendation results, in many real-world recommendation scenarios cold-start and data sparseness remain important problems. This paper presents a hybrid recommender system that integrates user demographics and item characteristics, around a collaborative filtering core based on user-item interactions. The recommender system is evaluated on Movie lens data (including genre information and user data) as well as real-world data from a discount coupon provider. We show that the inclusion of additional item and user information can have great impact on recommendation quality, especially in settings where little interaction data is available.

Using annotations on Mechanical Turk to perform supervised polarity classification of Spanish customer comments

One of the major bottlenecks in the development of data-driven AI Systems is the cost of reliable human annotations. The recent advent of several crowdsourcing platforms such as Amazon’s Mechanical Turk, allowing requesters the access to affordable and rapid results of a global workforce, greatly facilitates the creation of massive training data. Most of the available studies on the effectiveness of crowdsourcing report on English data. We use Mechanical Turk annotations to train an Opinion Mining System to classify Spanish consumer comments. We design three different Human Intelligence Task (HIT) strategies and report high inter-annotator agreement between non-experts and expert annotators. We evaluate the advantages/drawbacks of each HIT design and show that, in our case, the use of non-expert annotations is a viable and cost-effective alternative to expert annotations.

EUMSSI: a Platform for Multimodal Analysis and Recommendation using UIMA

The EUMSSI project (Event Understanding through Multimodal Social Stream Interpretation) aims at developing technologies for aggregating data presented as unstructured information in sources of very different nature. The multimodal analytics will help organize, classify and cluster cross-media streams, by enriching its associated metadata in an interactive manner, so that the data resulting from analysing one media helps reinforce the aggregation of information from other media, in a cross-modal semantic representation framework. Once all the available descriptive information has been collected, an interpretation component will dynamically reason over the semantic representation in order to derive implicit knowledge. Finally the enriched information will be fed to a hybrid recommendation system, which will be at the basis of two well-motivated use-cases. In this paper we give a brief overview of EUMSSI’s main goals and how we are approaching its implementation using UIMA to integrate and combine various layers of annotations coming from different sources.