WebSci11 (Koblenz, Germany – June 2011)
The 2011 edition of the Web Science Conference was the first of the series to be an ACM conference. WebSci11 was inherently interdisciplinary and integrated computer and information sciences with a multitude of disciplines including sociology, economics, political science, law, management, language and communication, geography and psychology. This conference was unique in the manner in which it brought these disciplines together in creative and critical dialogues, sessions and workshops. In particular, the Health Web Science workshop, which I co-chaired, aimed to investigate the application of the multi-disciplinary approach of Web Science to the area of health education and health care. The workshop was the occasion to discuss the importance of patient centered applications and to present the recent development in the field of crowd validation for patient opinion mining.

ISNN11 (Guilin, China – May 2011)
The Eighth International Symposium Neural Networks provided a high-level international forum for scientists, engineers and educators to present the state-of-the-art of neural network research and applications in diverse fields. The symposium featured plenary lectures given by worldwide renowned scholars, regular sessions with broad coverage, and some special sessions focusing on popular topics. In particular, I co-chaired the special session on social affective data mining and analysis (SADMA), whose main aim was to bring AI and Semantic Web researchers together across the disciplinary divide for possibly the very first time, for exploring the new frontiers of opinion mining and sentiment analysis. SADMA was also the occasion to present the recent development in the field of affective common sense reasoning.

Internship at MSRA (Beijing, China – February/June 2011)
This internship at Microsoft Research Asia (MSRA) aims to enable machines to better understand electronic text in natural human language. In particular, the project consists in merging Sentic Computing with other NLP techniques to further develop a universal probabilistic ontology that is more comprehensive than any of the existing ontologies. The ontology already contains 2.7 million concepts harnessed automatically from a corpus of 1.68 billion web pages and two years’ worth of search log data. Unlike traditional knowledge bases that treat knowledge as black and white, it enables probabilistic interpretations of the information it contains. The probabilistic nature then enables it to incorporate heterogeneous information in a natural way. The project will also explore potential applications, e.g. understanding user intent, that can benefit from the taxonomy.

Web Science Module at UHI (February/May 2011)
The Web is the largest human information construct in history. The Web is transforming society. In order to understand what the Web is, engineer its future and ensure its social benefit we need a new interdisciplinary field that we call Web Science. This module, born from a new collaboration between the Web Science Trust, the UHI Millennium Institute and Sitekit Labs, is the first Web Science module that aims to give undergraduates an overview of this novel discipline. It will be held via videoconference from MSRA and locally managed by Ian Barnes. The module will let students better understand what the Web is today, study its evolution, either from a technological and socio-cultural perspective and, hence, engineer its future and ensure its social benefit.

Collaboration with CAS (Beijing, China – October 2010/January 2011)
This collaboration with the Chinese Academy of Sciences (CAS) is part of the China-Scotland SIPRA programme and aims to collaboratively develop and apply novel machine learning and natural language processing based technologies in order to blend the Open Mind database (which will be extended with common sense knowledge expressed in Chinese) with any given ontology, and hence build a novel intelligent software engine that can auto-categorise and analyse documents for intelligent web applications. The software engine will also employ novel language modelling, sentimental classification and adaptation techniques for bi-lingual (English and Chinese) document analysis. The developed software engine will enable the development of intelligent semantic web applications whose content can dynamically adapt to the user, including through the use of multimodal emotion-sensitive conversational agents.

CSK10 (Arlington, USA – November 2010)
The aim of the 2010 AAAI fall symposium on common sense knowledge (CSK10) was to bring together the diverse elements of the common sense computing community to allow researchers who focus directly on building systems for acquiring or reasoning with common sense knowledge to connect with those who wish to use these resources to help tackle tasks within their industry or within AI itself. Our research work was presented by Robert Speer, who showed the community how we used graph mining and dimensionality reduction techniques to infer the polarity of over 5,700 concepts from the Open Mind corpus and, hence, provide the public with a resource for mining opinions from natural language text at a semantic, rather than just syntactic, level.

SDoW at ISWC10 (Shanghai, China – November 2010)
The 3rd international workshop Social Data on the Web (SDoW), co-located with the 9th International Semantic Web Conference (ISWC2010), brought together researchers, developers and practitioners involved in semantically-enhancing social media websites, as well as academics researching more formal aspect of these interactions between the Semantic Web and Social Web. The workshop aimed to discuss techniques, methods and applications that are appearing and that are required to manage the data from the Social Web using semantic technologies, taking into account social relations, information overload, aggregations and summaries, trust and privacy and other related research topics. We presented a troll filtering system that exploits several Sentic Computing tools and techniques to automatically detect and disarm web trolls.

IEEE ICSP10 (Beijing, China – October 2010)
The 2010 IEEE 10th International Conference on Signal Processing (ICSP10) aimed to provide a stimulating forum for a lot of scholars, engineers and graduate students from all over the world. This year, ICSP was held on 24th-28th October at Taiyangdao Hotel, in Beijing, and cerebrated its 20 years anniversary. The Program Committee received near 1500 submission from 34 nations and regions. On the bases of paper review by the program committee, 642 were selected for presentation at the conference and including in the conference proceedings. All papers were categorized into 34 parallel sessions for oral presentation. We presented, at AI & Neural Networks session, our recent developments in the field of Sentic Computing for patient centered applications, which were welcomed with a lot of interest and several questions from the ICSP community.

Internship at HP Labs (Bangalore, India – June/October 2010)
The main aim of this internship was to enable rich and intuitive experiences that deliver the value of computing and the internet for non-tech-savvy users. Novel techniques and architectures to radically simplify creation, consumption and discovery of web content/services through intuitive and familiar interaction paradigms were explored. In particular, Sentic Computing techniques were employed to reason on user interaction metadata and hence find intelligent ways of storing, searching and retrieving multimedia contents. The research adopted both a bottom-up approach, by focusing on the design of an intelligent digital photo management system, and a top-down approach, by concurrently defining the requirements of a personal multimedia content management system which will collect and manage personal data and metadata associated to user's photos, emails, blogs, reviews, bookmarks, etc.

Visiting the Media Lab (Boston, USA – April/June 2010)
This second visit to MIT Media Lab took place from end of April to beginning of June. It was very profitable to work again in such a vibrant environment, especially in the weeks preceding the Sponsor Week, during which all the groups were busier than usual at building prototypes and setting up demo stations. The mission was also a very good occasion to work shoulder to shoulder with the Common Sense Computing Group, especially Robert Speer and Catherine Havasi, on employing different techniques, such as blending and spectral association, to build a publicly available semantic resource for opinion mining. These ideas were then demoed, together with recent developments in the field of Sentic Computing, during the Media Lab Sponsor Week and submitted to the AAAI fall symposium on common sense knowledge.

WebSci10 (Raleigh, USA – April 2010)
The second Web Science conference was held on 26th-27th April in Raleigh, North Carolina, in co-location with WWW2010. Once again the main aim of the conference was to demonstrate the development, scope and relevance of the emerging field of Web Science.
The conference embraced physical and social science drawing on computer and engineering sciences, sociology, economics, political science, law, management geography and psychology. WebSci10 brought these disciplines together in creative and critical dialogue and crossed traditional disciplinary boundaries. The conference offered the chance to introduce the idea of Crowd Validation i.e. the use of Sentic Computing to mine and analyze patient opinions in order to make a comprehensive and dynamic evaluation of the UK National Health Service.

COST Training School (Caserta, Italy – March 2010)
The 3rd COST International Training School took place on 15th-19th March 2010, in Caserta, Italy. The school afforded a change of perspective in verbal and nonverbal communication, where the research focus moves from "communicative tools" to "communicative instances" and asks for investigations that take into account the environment and the context in which the communicative acts take place. The school furthered artificial cognitive research by creating a bridge between the most recent research in multimodal communication (taking into account gestures, emotions, social signal processing, etc.) and models of computations that exploit these signals and are aware of the context in which these signals are expressed. The school was the occasion to get useful feedback on the strategies and the techniques used to merge Sentic Computing with different tools for audio and video processing.

WOMSA at CAEPIA09 (Seville, Spain – November 2009)
On 13th November the recent developments in the field of Sentic Computing were presented in Seville at WOMSA, the first workshop on opinion mining and sentiment analysis within CAEPIA09 (the conference of the Spanish association for artificial intelligence). In a world in which millions of people write their opinions about any issue in blogs, news sites, review sites or social media, the distillation of knowledge from this huge amount of unstructured information is a challenging task. The topics of the workshop included opinion extraction and classification, opinion summarization and visualization, recommender systems, user generated content and social media analysis, blogs analysis, sentiment and subjectivity analysis. We presented AffectiveSpace, a multi-dimensional vector space obtained by applying singular value decomposition on the blend of ConceptNet and WordNet-Affect.

Innovate09 (Aviemore, UK – October 2009)
Innovate09 is the Technology Strategy Board's annual conference and exhibition. The day-long event addressed all aspects of technology innovation, with special focus on the commercial exploitation of a low carbon economy, energy generation and supply, the digital economy and life sciences of the future. Through high-level question-time style sessions, in depth seminars, and technology exhibits we were able to make new business connections and take away the tips, tricks and approaches that will inspire us to innovate. Innovate09 also provided a chance to hear about the latest funding opportunities that will allow business to commercialise research and development activities - whether by working with Innovation Platforms, or through collaborative R&D, Knowledge Transfer Partnerships, SBRI and European schemes.

BioID_MultiComm09 (Madrid, Spain – September 2009)
This international conference was organised cooperatively by COST Actions 2101 and 2102 to investigate novel technologies for unsupervised multimodal biometric authentication systems and develop an advanced acoustical, perceptual and psychological analysis of verbal and non-verbal communication signals, in order to identify algorithms and automatic procedures capable of recognizing human emotional states.
In this context, we presented our recent developments in the fields of text categorization and affective analysis through a paper, published by Springer, containing a review of the roots, the state of the art and the future trends of common sense computing, from Minsky's Society of Mind to Media Laboratory's Digital Intuition theory.

The Art of the Start (Edinburgh, UK – April 2009)
Guy Kawasaki is managing director of Garage Technology Ventures, an early-stage venture capital firm and a columnist for Entrepreneur Magazine. Previously, he was an Apple Fellow at Apple Computer Inc. Guy Kawasaki came to Edinburgh to help 100s of students, startups and investors understand better how to make the world a better place through startups. Among Guy's hints: start with the idea of making meaning in place of money, don't get stuck in one type of business but try to jump curves, don't be afraid of polarizing people, find a few soul mates because the road to success is long and tough, keep your business model simple, define the tasks required to open up your potential, enable people to test drive your product, don't ask users to do something that you wouldn't, surround yourself with people who are passionate about changing the world with your stuff.

COST2102 (Dublin, Ireland – March 2009)
The main focus of this international training school held at Trinity College was the development of multimodal interfaces with interdisciplinary focuses on speech, gesture and emotion. The last field was particularly interesting since one of the ideas of the project is to develop emotion-sensitive systems in the sector of e-health. Many useful information were gathered about the categorization of emotions and state of the art techniques to get emotions from text and speech. A talk was also given on 26th March about the use of common sense computing to enable the development of intelligent web applications capable to understand users also from an emotional point of view. The presentation interested many COST researchers and gave birth to a lot of questions about the Common Sense Computing Initiative.

WebSci09 (Athens, Greece – March 2009)
The aim of this conference was to bring computer scientists and social scientists together across the disciplinary divide, exploring the development of the web across different areas of everyday life and technological development. WebSci09 was the first Web Science conference organised by the Web Science Research Initiative (WSRI) and the Foundation of the Hellenic World (FHW) to be dedicated to the presentation of research into society on the web. The paper sessions were very useful to gather information about the state of the art of semantic web and about the main institutes, organizations and people working on it. The poster session offered the chance to look at other PhD projects and ideas in the area of Web Science and it was a first occasion to present officially the project research work. At last, the conference was very worthwhile to meet experts of the field such as Dame Wendy Hall and Sir Tim Berners-Lee, the inventor of the Web.

Visiting the Media Lab (Boston, USA – February 2009)
On February we visited the MIT Media Lab, a department within the School of Architecture and Planning at Massachusetts Institute of Technology, in Boston. Devoted to research projects at the convergence of multimedia and technology, the Media Lab was widely popularized in the 1990s by business and technology publications such as Wired and Red Herring for a series of practical inventions in the fields of wireless networks, field sensing, browsers and the world wide web. More recently it has focused on product design more generally, particularly for technologies that address social causes. The visit was the occasion for being initiated to the Open Mind Common Sense project and for meeting all the MIT researchers involved in the Common Sense Computing Initiative, especially Catherine Havasi, the external supervisor of this PhD research project, and Marvin Minsky, the father of AI.