| Abstract | Opinions play a major role to almost all human activities, because they are key influencers of our choices and way of thinking. Whenever we need to make a decision, we want to know others’ opinions on the subject at hand. In the real world, businesses
and organizations want to know consumer or public opinions about their products and services. On the other hand, individual consumers also want to know the opinions of
other people that have used a particular product, before purchasing it.
With the explosive growth of social networks (e.g. blogs, micro-blogs, forum, reviews, videos, comments and postings in social network sites) on the Web, a huge dataset has
been created, ready to be exploited to find user preferences and opinions. Sentiment analysis focuses on the task of automatically identifying whether a piece of text
expresses a positive or negative polarity about the subject matter. In this thesis, sentiment analysis is performed on Greek review and unboxing videos that are related
to tech products (mostly smartphones and laptops), using a sentiment lexicon. In addition, previous work in this area on Greek and the English languages is examined and compared.
|
