| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:HIBRIDNI PRISTOP ZA ZAZNAVO ELEMENTOV SUBJEKTIVNOSTI V BESEDILNIH TOKOVIH
Authors:ID Verlič, Mateja (Author)
ID Kokol, Peter (Mentor) More about this mentor... New window
ID Zorman, Milan (Comentor)
Files:.pdf DR_Verlic_Mateja_2009.pdf (2,68 MB)
MD5: D79D00773A7EAE71B2C8B85943E42F2B
PID: 20.500.12556/dkum/da602b30-a33d-4a3c-b13a-a967779299d0
 
Language:Slovenian
Work type:Dissertation
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Analiza razpoloženja je dokaj nova veja besedilnega rudarjenja, ki je zadnji čas še posebej priljubljena zaradi ogromnega potenciala za raziskovanje javnega mnenja na najrazličnejših področjih. Za razliko od priklica informacij in računalniške lingvistike, na katerih je osnovana, se analiza razpoloženja ne osredotoča na teme v dokumentu ali na objektivne informacije (o lokaciji, času,osebah), ampak na subjektivno mnenje, ki ga pisec izraža v dokumentu. Še posebej zanimiva je za analizo besedilnih tokov, ki so besedila s posebnimi lastnostmi dostopna na spletu. Obstaja veliko možnosti uporabe, na primer spremljanje mnenj o določenem produktu ali storitvi, spremljanje javnega mnenja o političnih kandidatih med volitvami ali o družbeno-političnih dogajanjih in podobno. Pri analizi razpoloženja ne gre le za zaznavanje mnenja, ampak tudi za izločitev ustreznih značilk, na podlagi katerih se mnenje opredeli kot pozitivno (dobro) ali negativno (slabo). V doktorski disertaciji smo raziskali polavtomatsko in avtomatsko prepoznavanje elementov subjektivnosti, ki so nosilci mnenja oziroma razpoloženja, na osnovi katerih smo zgradili slovarje za nadaljnjo klasifikacijo. Predstavili smo nov hibridni pristop h klasifikaciji razpoloženja in orodje, ki ta pristop implementira. V disertaciji smo združili ideje s področja strojnega učenja, priklica informacij, računalniške lingvistike in tudi s področja psihologije.
Keywords:analiza razpoloženja, rudarjenje mnenja, rudarjenje po besedilih, klasifikacija, strojno učenje
Place of publishing:Maribor
Publisher:[M. Verlič]
Year of publishing:2009
PID:20.500.12556/DKUM-12689 New window
UDC:004.6:004.55(043.3)
COBISS.SI-ID:13698838 New window
NUK URN:URN:SI:UM:DK:WHNX8XNA
Publication date in DKUM:11.12.2009
Views:3057
Downloads:377
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
VERLIČ, Mateja, 2009, HIBRIDNI PRISTOP ZA ZAZNAVO ELEMENTOV SUBJEKTIVNOSTI V BESEDILNIH TOKOVIH [online]. Doctoral dissertation. Maribor : M. Verlič. [Accessed 22 April 2025]. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=12689
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Similar works from other repositories:

No similar works found

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:Hybrid approach to detection of elements of subjectivity in text streams
Abstract:Sentiment analysis or opinion mining is relatively new branch of text mining and is very popular lately especially because of the potential for mining public opinion in different areas of interest. In comparison to Information retrieval and Computational Linguistics, opinion mining is not focused on topics or objective data (location, time, people) but on subjective opinion of the document writer. Sentiment analysis is especially interesting for analyzing text streams, which are texts with special characteristics available on the web. There are many possibilities of applying sentiment analysis, for example, it can be used to track opinions on some special product or service, tracking public opinion on political candidates during election time or on some political situations. Opinion mining is not only about determining opinions, but also to extract features that can be used to determine, whether opinion was positive (good) or negative (bad). This thesis describes we researched semi-automated and automated detection of subjective elements - terms bearing opinion or sentiment and which served as a basis for lexicons to be later used in classification. New hybrid method of sentiment classification has been proposed and implemented in our tool SentimentHitchhicker. Thesis combines ideas and methods from different fields, including machine learning, information retrieval, computer linguistics and psychology.
Keywords:sentiment analysis, opinion mining, text mining, machine learning


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica