Due to the many extension requests, the submission deadline of the IEEE CIM special issue on Computational Intelligence for Natural Language Processing has been postponed to the end of this week. For more/up-to-date info, please visit http://sentic.net/cinlp
RATIONALE The textual information available on the Web can be broadly grouped into two main categories: facts and opinions. Facts are objective expressions about entities or events. Opinions are usually subjective expressions that describe people's sentiments, appraisals, or feelings towards such entities and events. Much of the existing research on textual information processing has been focused on mining and retrieval of factual information, e.g., text classification, text recognition, text clustering, and many other text mining and natural language processing (NLP) tasks. Little work had been done on the processing of opinions until only recently.
One of the main reasons for the lack of studies on opinions is the fact that there was little opinionated text available before the recent passage from a read-only to a read-write Web. Before that, in fact, when people needed to make a decision, they typically asked for opinions from friends and family. Similarly, when organizations wanted to find the opinions or sentiments of the general public about their products and services, they had to specifically ask people by conducting opinion polls and surveys.
However, with the advent of the Social Web, the way people express their views and opinions has dramatically changed. They can now post reviews of products at merchant sites and express their views on almost anything in Internet forums, discussion groups, and blogs. Such online word-of-mouth behavior represents new and measurable sources of information with many practical applications. Nonetheless, finding opinion sources and monitoring them can be a formidable task because there are a large number of diverse sources and each source may also have a huge volume of opinionated text.
In many cases, in fact, opinions are hidden in long forum posts and blogs. It is extremely time-consuming for a human reader to find relevant sources, extract related sentences with opinions, read them, summarize them, and organize them into usable forms. Thus, automated opinion discovery and summarization systems are needed. Sentiment analysis grows out of this need: it is a very challenging NLP or text mining problem. Due to its tremendous value for practical applications, there has been an explosive growth of both research in academia and applications in the industry.
All the sentiment analysis tasks, however, are very challenging. Our understanding and knowledge of the problem and its solution are still limited. The main reason is that it is a NLP task, and NLP has no easy problems. Another reason may be due to our popular ways of doing research. So far, in fact, researchers have relied a lot on traditional machine learning algorithms. Some of the most effective machine learning algorithms, however, produce no human understandable results. Apart from some superficial knowledge gained in the manual feature engineering process, in fact, such algorithms may achieve improved accuracy, but little about how and why is actually known. All such approaches, moreover, rely on syntactic structure of text, which is far from the way human mind processes natural language.
TOPICS Articles are thus invited in area of computational intelligence for natural language processing and understanding. The broader context of the Special Issue comprehends artificial intelligence, knowledge representation and reasoning, data mining, artificial neural networks, evolutionary computation, and fuzzy logic. Topics include, but are not limited to: - Computational intelligence for big social data analysis - Biologically inspired opinion mining - Concept-level opinion and sentiment analysis - Computational intelligence for social media retrieval and analysis - Computational intelligence for social media marketing - Social network modeling, simulation, and visualization - Semantic multi-dimensional scaling for sentiment analysis - Computational intelligence for patient opinion mining - Sentic computing - Multilingual and multimodal sentiment analysis - Multimodal fusion for continuous interpretation of semantics - Computational intelligence for time-evolving sentiment tracking - Computational intelligence for cognitive agent-based computing - Human-agent, -computer, and -robot interaction - Domain adaptation for sentiment classification - Affective common-sense reasoning - Computational intelligence for user profiling and personalization - Computational intelligence for knowledge acquisition
TIMEFRAME August 4th, 2013: Paper submission deadline September 1st, 2013: Notification of acceptance October 1st, 2013: Final manuscript due February, 2014: Publication
SUBMISSION The maximum length for the manuscript is typically 25 pages in single column with double-spacing, including figures and references. Authors of papers should specify in the first page of their manuscripts corresponding author’s contact and up to 5 keywords. Submission should be made via email to one of the guest editors below.
GUEST EDITORS - Erik Cambria, National University of Singapore (Singapore) - Bebo White, Stanford University (USA) - Tariq S. Durrani, Royal Society of Edinburgh (UK) - Newton Howard, MIT Media Laboratory (USA)