ABSTRACT
Due to many challenging research problems and a wide variety of practical applications, opinion mining and sentiment analysis have become very active research areas in the last decade. Our understanding and knowledge of the problem and its solution are limited as natural language understanding techniques are still pretty weak. Most of current research in sentiment analysis, in fact, merely relies on machine learning algorithms. Such algorithms, despite most of them being very effective, produce no human understandable results such that we know little about how and why output values are obtained. All such approaches, moreover, rely on syntactical structure of text, which is far from the way human mind processes natural language. The main aim of this special session is to examine the new frontiers of opinion mining and sentiment analysis by proposing brain inspired techniques that could allow to better extract and aggregate the cognitive and affective information associated with natural language text.

TOPICS
The special session will provide an international forum for both researchers and entrepreneurs working in the field of opinion mining to share information on their latest investigations in social information retrieval and their applications in academic research areas and industrial sectors. The broader context of the special session comprehends Web Mining, AI, Semantic Web, Information Retrieval, and Natural Language Processing. In addition to paper presentations, organizers plan to solicit an invited talk or a panel that will stress the interdisciplinary challenges of opinion mining and sentiment analysis. Topics of interest include but are not limited to:
•  Brain inspired sentiment identification & classification
•  Brain inspired sentiment summarization & visualization
•  Brain inspired opinion search & retrieval
•  Brain inspired topic detection & trend discovery
•  Brain inspired sentiment corpora & annotation
•  Brain inspired applications to new social media
•  Brain inspired affective knowledge acquisition & representation
•  Brain inspired sentiment tracking
•  Brain inspired affect structures & models
•  Brain inspired comparative opinion analysis
•  Brain inspired cross-lingual sentiment analysis
•  Brain inspired sentiment elicitation from events
•  Brain inspired business intelligence applications

TIMEFRAME
•  March 19th, 2012: Due date for Special Session papers
•  April 30th, 2012: Notification of paper acceptance to authors
•  May 31st, 2012: Camera-ready of accepted papers
•  August 22nd, 2012: Special Session date

SUBMISSION AND PROCEEDINGS
The session number (SS4) must be shown in front of the title of each submission. Papers have to be submitted to both EasyChair and BIOMSA organizers, in order to track their reviews.
Accepted papers will be published in IEEE ICCI*CC proceedings. Selected, expanded versions of papers presented at the session will be published in special issues of the International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) and the International Journal of Software Science and Computational Intelligence (IJSSCI).

ORGANIZERS
•  Erik Cambria, National University of Singapore (Singapore)
•  Wenyin Liu, City University of Hong Kong (Hong Kong)
•  Amitava Das, Norwegian University of Science and Technology (Norway)
•  Feifei Xu, Shanghai University of Electric Power (China)
•  Dipankar Das, Jadavpur University (India)

ABSTRACT
Extreme Learning Machines (ELM) provide efficient unified solutions to generalized feedforward networks including but not limited to feedforward neural networks and kernel learning. ELM possesses unique features to deal with regression and (multi-class) classification tasks. Consequently, ELM offers significant advantages such as fast learning speed, ease of implementation, and least human intervene. ELM has good potential as a viable alternative technique for large-scale computing and artificial intelligence. Organized by EXQUISITUS, Centre for E‐City, School of Electrical and Electronic Engineering, Nanyang Technological University, ELM2012 will be held in the beautiful island-country of Singapore. This symposium will provide a forum for academics, researchers and engineers to share and exchange R&D experience on both theoretical studies and practical applications of the ELM technique. All accepted papers presented in this symposium will be published in special issues of reputable ISI indexed international journals. Potential journals include: Information Sciences, Neurocomputing, Soft Computing, and Neural Computing and Applications. No additional symposium proceedings are provided.

TOPICS
All the submissions must be related to ELM technique. Topics of interest include but are not limited to:
Theories
•  Universal approximation and convergence
•  Robustness and stability analysis
Algorithms
•  Real‐time learning/reasoning
•  Sequential and incremental learning
•  Kernel based algorithms
Applications
•  Time series prediction
•  Pattern recognition
•  Web applications
•  Biometrics
•  Bioinformatics
•  Power systems
•  Control engineering
•  Security
•  Compression
•  Human computer interface
•  Imbalanced data processing
•  Data analytics
•  Super/ultra large‐scale data processing

TIMEFRAME
June 1st, 2012: Paper submission deadline
October 15th, 2012: Registration deadline
September 1st, 2012: Notification of acceptance
December 11-13th, 2012: Conference dates

SUBMISSIONS
Only full‐length manuscripts with at least submission entry quality of good journals will be considered for presentation at this symposium. All the submissions will go through rigorous peer review. Details on manuscript submission will be given online http://extreme-learning-machines.org and by February 15th, 2012.

ABSTRACT
Opinions play a primary role in decision-making processes. Whenever people need to make a choice, they are naturally inclined to hear others’ opinions. In particular, when the decision involves consuming valuable resources, such as time and/or money, people strongly rely on their peers’ past experiences. Just a few years ago, the main sources for collecting such information were friends, acquaintances and, in some cases, specialized magazines or websites. The passage from a read-only to a read-write Web has provided people with new tools that allow them to create and share, in a timely and cost-efficient way, their own contents, ideas, and opinions with virtually millions of people connected to the World Wide Web. The opportunity to capture the opinions of the general public about social events, political movements, company strategies, marketing campaigns, and product preferences has raised more and more interest both in the scientific community, for the exciting emergent challenges, and in the business world, for the remarkable fallouts in marketing and financial market prediction. Mining opinions and sentiments from natural language, however, is an extremely difficult task: it involves a deep understanding of most of the explicit and implicit, regular and irregular, syntactical and semantic rules of a language. Existing approaches mainly rely on parts of text in which opinions and sentiments are explicitly expressed such as polarity terms, affect words, and their co-occurrence frequencies. However, opinions and sentiments are often conveyed implicitly through latent semantics, which make purely syntactical approaches ineffective. In this light, this special issue focuses on the introduction, presentation, and discussion of novel approaches to opinion mining and sentiment analysis that are not entirely based on domain-dependent corpora but also on general-purpose semantic knowledge bases. The main motivation for the issue, in particular, is to go beyond a mere word-level analysis of text and provide novel concept-level approaches to opinion mining and sentiment analysis that allow a more efficient passage from (unstructured) textual information to (structured) machine-processible data, in potentially any domain.

TOPICS
Articles are thus invited in areas such as AI, the Semantic Web, knowledge-based systems, and adaptive and transfer learning for research on opinion and sentiment retrieval and analysis. Potential topics include:
•  Opinion and sentiment summarization and visualization
•  Explicit and latent semantic analysis for opinion and sentiment mining
•  Knowledge base construction and integration with opinion and sentiment analysis
•  Transfer learning of opinion and sentiment with knowledge bases
•  Time-evolving opinion and sentiment analysis
•  Corpora and resources for opinion and sentiment analysis
•  Multimodal sentiment analysis
•  Multidomain and cross-domain evaluation
•  Multilingual sentiment analysis and reuse of knowledge bases

TIMEFRAME
July 1st, 2012: Paper submission deadline
September 16th, 2012: Notification of acceptance
November 11th, 2012: Final manuscript due
March/April, 2013: Publication

SUBMISSION AND PROCEEDINGS
The special issue will consist of papers on novel methods and techniques for building and using semantic knowledge bases in the field of opinion mining and sentiment analysis. Besides the specified topics of interest, the special issue also welcomes papers on specific application domains of sentiment analysis—for example, social data mining, influence networks, customer experience management, computer-mediated human-human communication, social media marketing, multimedia management, personalization and persuasion, enterprise feedback management, human-agent, -computer and -robot interaction, intelligent user interfaces, patient opinion mining, surveillance, and art. Submissions should be 3,000 to 5,400 words (counting a standard figure or table as 200 words) and should follow IEEE Intelligent Systems style and presentation guidelines. The manuscripts cannot have been published or be currently submitted for publication elsewhere. We strongly encourage submissions that include audio, video, and community content, which will be featured on the IEEE Computer Society Web site along with the accepted papers.

ORGANIZERS
•  Erik Cambria, National University of Singapore (Singapore)
•  Bjoern Schuller, Technical University of Munich (Germany)
•  Bing Liu, University of Illinois at Chicago (USA)
•  Haixun Wang, Microsoft Research Asia (China)
•  Catherine Havasi, MIT Media Laboratory (USA)

ABSTRACT
The ability to learn and understand natural language sounds obvious and natural to us but it is actually a daedal and multi-faceted process. The illusion of simplicity comes from the fact that, as each new group of skills matures, we build more layers on top of them and tend to forget about previous layers. Current attempts to perform automatic understanding of human language, e.g., textual entailment and machine reading, still suffer from numerous problems including inconsistencies, synonymy, polysemy, entity duplication and more, as they focus on a pure syntactical analysis of the information reaching the brain. If we want machines to literally understand natural language rather than merely simulating the ability to understand it, we need not only to investigate the synergies among the multi-modal and multi-sensorial data available to the machine, but also to go beyond a content-level analysis of natural language and aim for a concept- and context-level analysis, taking also the inevitably interactions with the environment into account. At the same time, as the natural language processing (NLP) techniques increase in realism and sensibility, more and more advanced evaluation procedures need to be explored and implemented to suitably assess the insightfulness of the developed technologies even in real application scenarios. The main aim of this BICS-12 Special Session is to examine the new frontiers of NLP by proposing brain-inspired techniques in fields such as computational intelligence, knowledge-based systems, multimedia (audio, video, textual) information processing, adaptive and transfer learning, in order to more efficiently extract useful information from human language which could lead to improved machine understanding and sustainable human-machine interfaces.

TOPICS
BINLP aims to provide an international forum for researchers in the field of natural language processing to share information on their latest investigations and their applications both in academic research areas and industrial sectors. The broader context of the Special Session comprehends AI, web mining, information retrieval, speech recognition, and opinion mining. Topics of interest include but are not limited to:
•  Knowledge-based natural language processing
•  Human language summarization and visualization
•  Explicit and latent semantic analysis for natural language processing
•  Time evolving human language analysis
•  Computational linguistics
•  Multi-domain natural language processing
•  Multi-lingual natural language processing
•  Multi-modal (spoken, typed, handwritten) natural language processing

TIMEFRAME
•  February 15th, 2012: Due date for Special Session papers
•  March 15th, 2012: Notification of paper acceptance to authors
•  April 5th, 2012: Camera-ready of accepted papers
•  July 11th, 2012: Special Session date

SUBMISSION AND PROCEEDINGS
Prospective authors are invited to submit full-length papers (6-8 pages normally and 10 pages maximum) by the submission deadline through the online submission system. The submission of a paper implies that the paper is original and has not been submitted under review or copyright protected elsewhere and will be presented by an author if accepted. All submitted papers will be refereed by experts in the field based on the criteria of originality, significance, quality, and clarity. The authors of accepted papers will have an opportunity to revise their papers and take consideration of the referees’ comments and suggestions. All papers accepted by and presented at BICS 2012 will be published by Springer as multiple volumes of Lecture Notes in Artificial Intelligence which will be indexed by EI and ISTP. Selected papers will be published in special issues of several SCI journals.

ORGANIZERS
•  Erik Cambria, National University of Singapore (Singapore)
•  Stefano Squartini, Marche Polytechnic University (Italy)
•  Amir Hussain, University of Stirling (UK)
•  Newton Howard, MIT Media Laboratory (USA)

ABSTRACT
Cognitive and Emotional Information Processing techniques have encountered a large success within the scientific community, specially due to the impact they naturally have in diverse application fields as commerce, tourism, education and health. A wide number of advanced solutions have been proposed on purpose spanning from User/Web Interfaces and Mobile Computing to Robotics, Ambient Intelligence, and Computer Support to Collaborative Work/Learning. The objective is devoted to adequately interpret humans’ opinions, tastes and needs and consequently provide not only useful direct feedback to them but also a valid and natural support to the interactions they can have between themselves and with smart cooperative environments. This asks for development of expert systems, able to manage large amount of information coming from sensory activity, to intelligently process it, and to promptly and knowledgeably respond to human actions according to natural interaction standards and by means of suitable actuary devices. Information processing therefore plays a central role from this perspective, operating at different levels, from multimodal digital data manipulation to semantic metadata processing, and necessarily encompassing the most challenging computational intelligence paradigms for contextual adaptation, social-emotional competence, and cognitive reasoning abilities. Moreover, if on one hand the distillation of knowledge from such type data is a key factor for most of the applications it must be also said on the other hand that the extremely unstructured nature of these contents and their exponentially growing size make it a very difficult task to be faced. Information scientists working in related areas such as multimedia, machine learning, knowledge management, affective computing or semantic web are invited to contribute to attain the above research aims, by sharing their expertise in this emerging interdisciplinary field, and at the same time paving the way to new exciting research topics in the cognitive and emotional information processing field.

TOPICS
Topics of interest include but are not limited to:
•  Socio-Emotional Data Processing Techniques and Applications
•  Human Behaviour Analysis and Understanding
•  Cognitive Systems for Multimodal Interaction
•  Cognitive-Emotional Models in Cooperative Scenarios
•  Computational Intelligence Techniques for Affective Computing
•  Semantic Information Processing
•  Multimedia-interfaced Systems for Human-Machine Interaction

TIMEFRAME
•  February 15th, 2012: Due date for Special Session papers
•  March 15th, 2012: Notification of paper acceptance to authors
•  April 5th, 2012: Camera-ready of accepted papers
•  July 11th, 2012: Special Session date

SUBMISSION AND PROCEEDINGS
Prospective authors are invited to submit full-length papers (6-8 pages normally and 10 pages maximum) by the submission deadline through the online submission system. The submission of a paper implies that the paper is original and has not been submitted under review or copyright protected elsewhere and will be presented by an author if accepted. All submitted papers will be refereed by experts in the field based on the criteria of originality, significance, quality, and clarity. The authors of accepted papers will have an opportunity to revise their papers and take consideration of the referees’ comments and suggestions. All papers accepted by and presented at BICS 2012 will be published by Springer as multiple volumes of Lecture Notes in Artificial Intelligence which will be indexed by EI and ISTP. Selected papers will be published in special issues of several SCI journals.

ORGANIZERS
•  Stefano Squartini, Marche Polytechnic University (Italy)
•  Erik Cambria, National University of Singapore (Singapore)
•  Francesco Piazza, Marche Polytechnic University (Italy)
•  Bjoern Schuller, Technical University of Munich (Germany)

Applicants should have a good honors degree in Computer Science or similar, as well as relevant experience in conducting research in the field. The ideal candidate should have basic understanding in knowledge representation and natural language processing, and should be able to work independently on such tasks as literature review, programming and data management.

Remuneration will be commensurate with qualifications and experience.
Interested applicants should send their CV to
 me

ABSTRACT
To date, the majority of sentiment analysis research has been focused on English language. But, recent studies show that non-native English speakers support the growing use of Internet. Although a few isolated research endeavors have been noticed by a few research groups for Asian languages like Chinese, Japanese, Thai and for other Indo-Aryan languages like Bengali, Hindi etc., more and more research efforts are required to meet the demands of the real life multilingual environment. In the present scenario, this special session aims to provide a platform to Asian sentiment analysis researchers for discussing the sentiment analysis challenges and solutions methodologies for their respective languages.
Natural language processing research endeavor primarily depends on the availability of resources like corpus, lexicon etc. For that reason, sentiment analysis research for Asian languages is still striving as for the scarcity of resources like sentiment lexicon or corpus. Firstly, the expected issues for the present special session are the generation of sentiment resources for the Asian languages. Secondly, this special session would like to encourage the cultivation of sentiment analysis research by discussing the challenges and methodologies for the rich morpho-syntactic Asian languages. Finally, our plan is to make a common portal by which the Asian researchers can access and share sentiment analysis resources for their own languages. We strongly recommend every active Asian sentiment analysis research group to contribute their research efforts in this special session.

TOPICS
Topics of interest include, but are not limited to:
•  Generation of Sentiment Analysis Resources for Asian Languages
•  New methodologies of Sentiment Analysis for Asian Languages
•  Evaluation methodologies
•  Applications of Sentiment Analysis for Asian Languages
•  Sentiment Search Engines for Asian Languages
•  Applications of sentiment analysis
•  Machine Translation for Sentiment Analysis
•  Knowledge-Based Systems for Sentiment Analysis

TIMEFRAME
•  January 6th, 2012: Due date for Special Session papers
•  February 6th, 2012: Notification of paper acceptance to authors
•  March 1st, 2012: Camera-ready of accepted papers
•  June 12th, 2012: Special Session date

ORGANIZERS
•  Amitava Das, Jadavpur University (India)
•  Erik Cambria, National University of Singapore (Singapore)

ABSTRACT
Memory and data capacities double approximately every two years and, apparently, the Web is following the same rule. User-generated contents, in particular, are an ever-growing source of opinion and sentiments which are continuously spread worldwide through blogs, wikis, fora, chats and social networks. The distillation of knowledge from such sources is a key factor for applications in fields such as commerce, tourism, education and health, but the quantity and the nature of the contents they generate make it a very difficult task. Existing approaches to opinion mining and sentiment analysis can be grouped into four main categories: keyword spotting, in which text is classified according to the presence of fairly unambiguous affect words; lexical affinity, which assigns arbitrary words a probabilistic affinity for a particular emotion or opinion polarity; statistical methods, which calculate the valence of keywords and word co-occurrence frequencies on the base of a large training corpus; finally sentic computing, which uses affective ontologies and common sense reasoning tools for a concept-level analysis of natural language text.

TOPICS
SENTIRE aims to provide an international forum for researchers in the field of opinion mining and sentiment analysis to share information on their latest investigations in social information retrieval and their applications both in academic research areas and industrial sectors. The broader context of the workshop comprehends Web mining, AI, Semantic Web, information retrieval and natural language processing. Topics of interest include but are not limited to:
•  Opinion & sentiment summarization and visualization
•  Explicit and latent semantic analysis for opinion & sentiment mining
•  Knowledge base construction and integration with opinion & sentiment analysis
•  Transfer learning of opinion & sentiment with knowledge bases
•  Time evolving opinion & sentiment analysis
•  Opinion & sentiment extraction and retrieval

INVITED SPEAKER
Bing Liu is a professor of Computer Science at University of Illinois at Chicago (UIC). He received his PhD in Artificial Intelligence from the University of Edinburgh. Before joining UIC, he was with the National University of Singapore. His current research interests include opinion mining and sentiment analysis, Web mining, and data mining. He has published extensively in leading conferences and journals in these fields. He has also written a textbook titled “Web Data Mining: Exploring Hyperlinks, Contents and Usage Data” published by Springer. The second edition of the book came out in July 2011. On professional services, Liu has served as program chairs of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), IEEE International Conference on Data Mining (ICDM), ACM Conference on Web Search and Data Mining (WSDM), SIAM Conference on Data Mining (SDM), ACM Conference on Information and Knowledge Management (CIKM), and Pacific Asia Conference on Data Mining (PAKDD). Additionally, he has also served as associate editors of IEEE Transactions on Knowledge and Data Engineering (TKDE), Journal of Data Mining and Knowledge Discovery (DMKD), and SIGKDD Explorations, and is on the editorial boards of several other journals.

TIMEFRAME
•  August 5th, 2011: Due date for workshop papers
•  September 20th, 2011: Notification of paper acceptance to authors
•  October 14th, 2011: Camera-ready of accepted papers
•  December 11th, 2011: Workshop date

PROCEEDINGS
Accepted papers will be published in ICDM SENTIRE proceedings. Selected, expanded versions of papers presented at the workshop will be published in a follow-on Special Issue of Springer’s Cognitive Computation journal.

ORGANIZERS
•  Erik Cambria, National University of Singapore (Singapore)
•  Yangqiu Song, Microsoft Research Asia (China)
•  Catherine Havasi, MIT Media Laboratory (USA)
•  Amir Hussain, University of Stirling (UK)

ABSTRACT
In the western world, we live in an aging population who potentially require more medical support for longer. The current model for supporting this greater need for health care is not sustainable. The web may form one route to finding solutions which will alleviate this situation. Commerce, education, entertainment and individuals have embraced the potential of the world wide web and seen revolutionary benefits as they the way they operate. Indeed the users of the web have influenced the development of the web, co-creating it in the form which it exists today. Can Health provision and education move into the area of the web and create an environment where individuals and communities become more responsible for their own health and where possible, treatment? There has been increasing interest internationally in E-Health, Health 2.0, Medicine 2.0.

TOPICS
This workshop aims to investigate the application of the discipline of Web Science to the area of Health education and Health care. Full Papers and position papers are invited in this area. Topics which may be covered include:
•  Engaging individuals in services provided via the web
•  Personalization of Health Applications and data input via the web
•  Engaging communities in services and as communities on the web
•  Evaluation of Health Web Services
•  Future directions of Health services using the Web

TIMEFRAME
•  May 9th, 2011: Due date for workshop papers
•  May 23rd, 2011: Notification of acceptance
•  June 15th, 2011: Workshop date

SUBMISSION
Prospective authors are invited to submit original papers of no more than 8 pages in the ACM SIG Proceedings templates format or position papers of no more than 2 pages. Papers should be submitted electronically in PDF format. Selected papers will be published on the conference website. Authors will be given the opportunity to present their papers at the workshop. Submissions should be sent to healthwebsci11(at)uhi.ac(dot)uk.

ORGANIZERS
•  Elizabeth Brooks, University of Highlands and Islands (UK)
•  Grant Cumming, University of Highlands and Islands (UK)
•  Michael Rayner, University of Highlands and Islands (UK)
• Catherine Pope, University of Southampton (UK)
•  Mark Weal, University of Southampton (UK)
•  Christopher Baker, University of New Brunswick (Canada)
•  Erik Cambria, University of Stirling (UK)
•  Joanne Luciano, Rensselaer Polytechnic Institute (USA)
•  Chris Eckl, Sitekit Solutions Ltd. (UK)

ABSTRACT
The transformation of the Web from its humble read-only origins to the current interactive/read-write medium has made its users ever more keen to share their sentiments and opinions through blogs, wikis, fora, chats and social networks, giving birth to a sort of social affective intelligence that emerges from the integration, competition and cooperation of web-users. The distillation of knowledge from such type of social affective data is a key factor for applications in fields such as commerce, tourism, education and health, but the extremely unstructured nature of these contents and their exponentially growing size make it a very difficult task. Such a challenge requires the ability to both represent and perform reasoning on social affective data, tasks which have been separately undertaken by Semantic Web and AI researchers respectively, exploiting techniques such as RDF schemas, triple stores, ontology languages, machine learning, neural networks and computational intelligence. The main aim of SADMA is to bring these two complementary groups together across the disciplinary divide for possibly the very first time, exploring the new frontiers of opinion mining and sentiment analysis.

TOPICS
•  Social affective data mining, search, query and ranking
•  Social affective data analysis, tagging, indexing and classification
•  Social affective data creation, editing, authoring and sharing
•  Social affective data processing techniques and applications

TIMEFRAME
•  December 1st, 2010: Due date for special session papers
•  January 1st, 2011: Notification of acceptance to authors
•  February 1st, 2011: Camera-ready of accepted papers
•  June 1st, 2011: Special session date

ORGANIZERS
•  Amir Hussain, University of Stirling (UK)
•  Tariq S. Durrani, University of Strathclyde (UK)
•  Newton Howard, MIT Media Laboratory (USA)
•  Erik Cambria, University of Stirling (UK)