2026-09-23T07:38:22Zhttps://iris.unica.it/oai/request

oai:iris.unica.it:11584/2668732022-10-15T19:58:02Zcom_11584_207615com_11584_111066col_11584_265854

The predictor impact of Web Search and Social Media MATTA, MARTINA Google Trends Sentiment Analysis Social Media Twitter Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni In recent years, web search and social media have emerged online. Search engine technology has had to speed up to keep up with the growth of the World Wide Web, that has turned the Internet into a wide information space with different and badly managed content. Millions of people all over the world search online several information each day, which makes Web search queries a valuable source of information. Due to the huge amount of available information, searching has become dominant in the use of Internet. Users that daily interact with search engines, produce valuable sources of interesting data regarding several aspects of the world. Social media increasingly pervades life in several fields of the world, enabling communication among users and collecting massive amount of information for social media companies that want to refine their products. Popular services like Twitter and Facebook attract a lot of users who share facts of their daily life. This kind of content has become more present on the web and, due to its public nature, even appears in search results from search engines, like Google and Bing. With the explosion of user generated content, came the need by politicians, analysts, researcher to monitor the content of different users. During my PhD, I decided to investigate whether social media activity or information collected by web search media could be profitable and used for predictive purposes. I studied whether some relationship exists between particular phenomena and volume of search data, considering the examined topic on web engines. Then, I analyzed the related social volume in order to discover whether the chatter of the community can be used to make qualitative predictions about the considered phenomena, attempting to establish whether there is any correlation. Simultaneously, I decided to apply automated Sentiment Analysis on shared short messages of users on Twitter in order to automatically analyze people opinions, sentiments, evaluations and attitudes 2016-03-04 info:eu-repo/semantics/doctoralThesis http://hdl.handle.net/11584/266873 eng numberofpages:95 info:eu-repo/semantics/openAccess Università degli Studi di Cagliari license:Non specificato