| dc.contributor.author | Bučar, Jože |
| dc.date.accessioned | 2017-05-09T11:03:02Z |
| dc.date.available | 2017-05-09T11:03:02Z |
| dc.date.issued | 2017-05-09 |
| dc.identifier.uri | http://hdl.handle.net/11356/1112 |
| dc.description | The JOB lexicon for sentiment analysis of Slovenian texts contains a list of 25,524 headwords from the List of Slovenian headwords 1.1 (http://hdl.handle.net/11356/1038) extended with sentiment ratings based on the AFINN model with an integer between -5 (very negative) and +5 (very positive). The ratings are derived from the lemmatized version of the Manually sentiment annotated Slovenian (sentence-based) news corpus SentiNews 1.0 (http://hdl.handle.net/11356/1110). |
| dc.language.iso | slv |
| dc.publisher | Faculty of Information Studies Novo mesto |
| dc.relation.isreferencedby | https://doi.org/10.1007/s10579-018-9413-3 |
| dc.rights | Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) |
| dc.rights.uri | https://creativecommons.org/licenses/by-sa/4.0/ |
| dc.rights.label | PUB |
| dc.source.uri | https://github.com/19Joey85/Sentiment-annotated-news-corpus-and-sentiment-lexicon-in-Slovene/ |
| dc.subject | sentiment lexicon |
| dc.subject | opinion lexicon |
| dc.title | Slovene sentiment lexicon JOB 1.0 |
| dc.type | lexicalConceptualResource |
| metashare.ResourceInfo#ContentInfo.detailedType | wordList |
| metashare.ResourceInfo#ContentInfo.mediaType | text |
| has.files | yes |
| branding | CLARIN.SI data & tools |
| contact.person | Jože Bučar joze.bucar@gmail.com Faculty of Information Studies Novo mesto |
| sponsor | ARRS (Slovenian Research Agency) MR-35498 Young Researcher Programme nationalFunds |
| sponsor | Human Resources Development and Scholarship Fund, Ministry of Education, Science and Sport, Slovenia 11012-55/2015 Javni razpis financiranja raziskovalnega sodelovanja doktorskih študentov v tujini v letu 2014 (186. JR) nationalFunds |
| sponsor | The European Regional Development Fund Operational Programme for Strengthening Regional Development Potentials for the period 2007-2013 Other |
| size.info | 25524 entries |
| files.count | 2 |
| files.size | 712761 |
Files in this item
Download all files in item (696.06 KB)This item is
Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Publicly Available
and licensed under:Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
- Name
- readme.txt
- Size
- 2.82 KB
- Format
- Text file
- Description
- readme file
- MD5
- d4b6fe03066bfdb7e48f146fe897d196
Title: Slovene sentiment lexicon JOB 1.0
Author: Jože Bučar, Faculty of Information Studies Novo mesto (contact: joze.bucar@gmail.com)
Abstract:
The JOB lexicon for sentiment analysis of Slovenian texts contains a list of 25524 headwords from the List of Slovenian headwords 1.1 (http://hdl.handle.net/11356/1038) extended with sentiment ratings based on the AFINN model with an integer between -5 (very negative) and +5 (very positive). The ratings are derived from the lemmatized version of the Manually sentiment annotated Slovenian (sentence-based) news corpus SentiNews 1.0 (http://hdl.handle.net/11356/1110).
Model:
The original sentence-level annotations were based on the five-level Lickert scale (integer between one (very negative) and five (very positive)). Therefore, we used linear transformation to transform average scores of sentences from the Lickert model to the AFINN (score one within the Lickert model transformed to minus five within the AFINN model, score five wit . . .
- Name
- Slovene_sentiment_lexicon_JOB.txt
- Size
- 693.23 KB
- Format
- Text file
- Description
- sentiment lexicon
- MD5
- 57bc2cc1c5b7349ec18cb256b2234c09
Word AFINN freq avg_AFINN sd_AFINN
a 0 3415 -0.466 1.787
aa -1 57 -1.116 1.367
ab -1 6 -1.277 2.189
aba -1 5 -0.610 1.046
abančen 0 3 -0.443 1.443
abc 0 28 0.121 1.564
abe -1 1 -0.860 0.000
abeceda 0 1 0.390 0.000
abeceden 2 3 1.640 2.500
abecednik 2 1 1.640 0.000
abjar 4 1 4.140 0.000
abonent 2 3 2.057 0.722
abonentski 2 3 1.779 0.241
abonma 0 8 0.182 2.294
abonmajski 0 1 0.390 0.000
abraham 0 4 0.390 1.768
absoluten 1 36 0.598 2.069
absolutist -2 1 -2.110 0.000
absolutističen 0 1 0.390 0.000
absolvent 0 5 -0.339 2.215
absolventski 0 1 0.390 0.000
absorbirati 0 5 -0.235 1.250
absorpcijski 2 2 1.640 0.000
abstiniranje 3 2 2.890 0.000
absurd -1 10 -1.402 1.608
absurden -1 19 -1.215 1.395
absurdno 1 2 1.015 0.884
absurdnost -2 1 -2.110 0.000
abs. 3 1 2.890 0.000
ac 0 18 0.390 2.134
act 0 1 0.390 0.000
ad 0 15 -0.304 1.914
adam 1 6 1.223 2.041
adaptacija 2 4 1.640 0.000
adaptirati 0 1 0.390 0.000
adenski -2 1 -2.110 0.000
adidas 1 12 1.185 3.273
adida . . .