Search results

The purpose of this paper is to propose a framework for intelligent analysis of Twitter data. The purpose of the framework is to allow users to explore a collection of tweets by extracting topics with semantic relevance. In this way, it is possible to detect groups of tweets related to new technologies, events and other topics that are automatically discovered.

The framework is based on a three-stage process. The first stage is devoted to dataset creation by transforming a collection of tweets in a dataset according to the vector space model. The second stage, which is the core of the framework, is centered on the use of non-negative matrix factorizations (NMF) for extracting human-interpretable topics from tweets that are eventually clustered. The number of topics can be user-defined or can be discovered automatically by applying subtractive clustering as a preliminary step before factorization. Cluster analysis and word-cloud visualization are used in the last stage to enable intelligent data analysis.

The authors applied the framework to a case study of three collections of Italian tweets both with manual and automatic selection of the number of topics. Given the high sparsity of Twitter data, the authors also investigated the influence of different initializations mechanisms for NMF on the factorization results. Numerical comparisons confirm that NMF could be used for clustering as it is comparable to classical clustering techniques such as spherical k-means. Visual inspection of the word-clouds allowed a qualitative assessment of the results that confirmed the expected outcomes.

The proposed framework enables a collaborative approach between users and computers for an intelligent analysis of Twitter data. Users are faced with interpretable descriptions of tweet clusters, which can be interactively refined with few adjustable parameters. The resulting clusters can be used for intelligent selection of tweets, as well as for further analytics concerning the impact of products, events, etc. in the social network.

The aim of this paper is the development of a modular robotic system for generic industrial applications, including assembly.

A library of robotic modules has been designed; they are divided into two categories: link modules, not actuated, and joint modules, actuated; the library is characterized by a relatively low number of elements, but allows the assembly of a wide variety of medium‐size serial robots.

The prototypes of two joint modules (a revolute joint module and a wrist module) and of some link modules have been realized. The behaviour of several serial robots composed of the designed modules has been assessed by multibody simulation. The results confirm the goodness of the proposed approach.

The two prototype modules are under test in combination with simplified modules. The further steps of the research programme will be the completion of the prototype library, and an experimental campaign on different serial chains.

Modularity allows one to achieve a great variety of robots starting from a small set of modules, in order to match different operative requirements. Moreover, modularity dramatically reduces the time‐to‐repair of the robot and consequently improves its overall availability; this is a fundamental feature for modern industrial enterprises aiming at maximizing the resources availability.

The proposed mechanical design of the revolute joint modules, based on a harmonic drive that connects two bodies in relative rotational motion, is compact and robust. Modularity is not restricted to mechanics: a distributed control system is adopted to make the reconfiguration of the robot easier and quicker.