01.02.2010 Submission system is now open.
10.03.2010 Paper submission extended deadline: March 21, 2010
Recent years have marked the beginning and expansion of the Web 2.0, i.e. the "Social web", characterized by increasing worldwide communication and, as a consequence in subjectivity. Specialists in market analysis and also IT fields such as Natural Language Processing, demonstrated that in the context of the newly created opinion phenomena, decisions for economic action (i.e. where to launch a product) are not only given by factual information, but are extremely affected by rumors and opinions given by non-specialists. Moreover, studies showed that the financial information presented in news articles is highly correlated to social phenomena, on which opinions are expressed in blogs, forums or reviews. On the one hand, many tasks that involve extensive efforts from the companies' marketing departments would be easier to perform with an automatic mass opinion mining process. An example is related to market research for business intelligence and competitive vigilance. New forms of expression on the web made it easier to collect information of interest, which can help to detect changes in the market attitude, discover new technologies, machines, markets where products are needed and detect possible threats from other companies. On the other hand, exploiting the results obtained analysing opinion information, companies can spot the market segments their products are best associated with and can enhance their knowledge on the clients they are addressing and on competitors. The analysis of opinions expressed by people with different background on the web can lead to the spotting of differences between the companies' products and the necessities expressed by clients and also between the companies' capacities and those of the competitors.
Mass opinion mining is related both to subjectivity and sentiment analysis, two tasks of growing importance in the field of Natural Language Processing (NLP), as well as other disciplines such as economics, psychology and sociology. Although studied separately, the task can benefit from an interdisciplinary approach, due to its difficulty and the multitude of facets that it contains.
The aim of this workshop is to bring together researchers in computational linguistics, dealing with subjectivity and sentiment analysis, but also from other disciplines related to the task of mass opinion mining and/or estimation: psychologists, sociologists, economists etc., with the objective of facilitating an interdisciplinary dialogue on the analysis, requirements, issues and applications of the study and modelling of mass opinion.
Download the pdf version of the CFP.
We welcome original and unpublished evaluation or position papers on all (mass) opinion mining issues. Some suggested topics include, but are not limited to:
- Mass opinion estimation based on NLP and statistical models
- Opinion mining and behavioural studies in the context of social networks
- Opinion retrieval, extraction, categorization, aggregation and summarization
- Information bias and perspective determination for source trust and reputation determination
- Computational analysis of persuasion techniques
- Correlation of factual and opinionated data based on socio-economic models
- User profile definition for personalized retrieval
- Topic relevance analysis for information monitoring
- Topic and sentiment studies and applications of topic-sentiment analysis
- Use of Semantic Web technologies for factual and subjective data analysis
- Proposals involving the computational treatment of large amounts of subjective data
- Applications of opinion mining systems to real-world business scenarios