Thesis topic proposal
Richárd Farkas
Sentiment analysis through deep natural language processing


Institute: University of Szeged
computer sciences
PhD School in Computer Science

Thesis supervisor: Richárd Farkas
Location of studies: SZTE
Abbreviation of location of studies: SZTE

Description of the research topic:

Recently, the popularity of social media has increased. People post
messages on a variety of topics, like products and political issues and
a large amount of user generated data is created in textual form.
Several applications have been developed for exploiting the knowledge
and information present in user generated content, like sentiment
analysis whose task is to assign polarity labels (positive, negative and
neutral) to textual elements.

Sentiment analysis can be applied at different levels depending on the
depth of information which we would like to extract from the texts. Most
of the available systems seek to identify the global sentiments of of a
particular document (e.g. a tweet or product review). The chief
objective of the doctoral topic is to addresses deep sentiment analysis.
We step beyond the bag-of-word model and utilize deep natural language
processing techniques to investigate each sentences. For understanding
the sentiment content of the following sentence, the research on new
syntax and semantics-based methods is required. "The menu is limited but
almost all of the dishes are excellent."

Required language skills: angol
Further requirements: 
Research topic for foreign applicants.

Number of students who can be accepted: 1

Deadline for application: 2017-03-31

All rights reserved © 2007, Hungarian Doctoral Council. Doctoral Council registration number at commissioner for data protection: 02003/0001. Program version: 1.2334 ( 2017. I. 15. )