Sentiment analysis is the automated evaluation of the average opinion of a given audience on any subject of interest. Web sentiment analysis bases this evaluation on information retrieved from the Web. While most research in this area focuses on natural language interpretation, Chiara Francalanci takes a data quality perspective and aims at improving the ability of sentiment analysis tools to interpret, weight, and combine multi-source information by exploiting domain-specific knowledge. The data quality field provides a consolidated body of research that highlights and classifies quality issues with both structured and unstructured data. These previous results help understand how the integration of information from multiple sources can either increase or decrease the overall quality of resulting data depending on how integration is performed. Chiara Francalanci's research applies these principles to multi-source sentiment analysis based on Web information.

The Web is a huge and heterogeneous source of information. Web 2.0 technologies have enabled an active role of the users, who can create and make available their contents very easily. This allows people to express their opinions, and to distribute them through several means, such as forums, blog posts and comments, social networks, and so on. Therefore, it becomes possible to access other people opinions and spread ideas bypassing traditional and official sources of information such as corporate websites. The availability of such an amount of information raises a set of issues concerning the research, the selection, and the representation of trustworthy sources and services. The information retrieved on the Web is indeed often characterized by inconsistent, incomplete, and not correct data, and users are not able to distinguish the right or the most suitable data along their needs. Furthermore, accessible sources can be better exploited if they are combined so that to obtain a tangible added value. Chiara Francalanci's work in this area tackles these issues with the goal of providing users with personalized self-service environments through which they can build their view over the Web information space, by integrating trustworthy services for information access.