| 1 |
Quantifying Social Semantics: an Inclusive Definition of Socialness and Ratings for 8,388 English Words ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Psycholinguistic norms for more than 300 lexical signs in German Sign Language (DGS) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Iconicity ratings across the Japanese lexicon: A comparative study with English ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
An Experimental Study on Building A Chinese Domain-Dependent Sentiment Lexicon
|
|
|
|
In: ISSN: 1225-2522 ; Journal of Language Sciences ; https://hal.archives-ouvertes.fr/hal-03242087 ; Journal of Language Sciences, 2020, 27 (4), pp.239-272. ⟨10.14384/kals.2020.27.4.239⟩ ; http://journal.alskorea.or.kr/read.php?pageGubun=journalsearch&pageNm=article&search=&journal=%EC%A0%9C27%EA%B6%8C%204%ED%98%B8&code=386031&issue=29046&Page=2&year=2020&searchType=all&searchValue= (2020)
|
|
Abstract:
International audience ; This study proposes an experimental approach to building a domain-dependent sentiment lexicon, a crucial resource for sentiment analysis of Chinese texts, in the Deco Sentiment Analysis platform developed at the Digital Language and Knowledge Contents Research Association (DICORA) research center. More than 150,000 hotel reviews were used for training with word2vec models, and 80 emotional words were first selected as seed words. TF-IDF was used to measure the relevance of the sentiment vocabulary in hotel reviews. In order to build the feature vector representation of each candidate word, the similarities between a term and the other 80 seed words were calculated. Then, expanding the lexicon involved a double propagation method that requires recognizing feature words related to the sentiment expressions. Through the bootstrap of sentiment terms and features, the expansion of the sentiment lexicon could be performed. The evaluation of the expanded result is confirmed with rates set at 77.4% of precision and 92.6% of recall performance.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; Annotated corpus; Avis de consommateurs; Chinese; Chinois; Corpus annoté; Dictionnaire pour le TAL; Double propagation; Expansion lexicale; Hotel recommendation; Lexicon expansion; Lexique des sentiments; NLP dictionary; Recommandation d'hôtels; Reviews and ratings; Sentiment lexicon; Word2vec
|
|
URL: https://doi.org/10.14384/kals.2020.27.4.239
https://hal.archives-ouvertes.fr/hal-03242087
|
|
BASE
|
|
Hide details
|
|
|
| 6 |
From Abstract Symbols to Emotional (In-)Sights ... : An Eye Tracking Study on the Effects of Emotional Vignettes and Pictures ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Language and Thought in the Motion Domain: Methodological Considerations and New Empirical Evidence. ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Language and Thought in the Motion Domain: Methodological Considerations and New Empirical Evidence
|
|
Feinmann, Diego. - : Springer US, 2020. : Journal of Psycholinguistic Research, 2020
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Correlations of concreteness and imageability ratings between studies.
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Numbers of publications on abstract and concrete concepts or words plotted over six decades.
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Correlations of concreteness ratings, word frequency, age-of-acquisition (AoA), zRT, and error rate.
|
|
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Correlation of the present concreteness ratings and word frequency [36], r = -.01, p = .17.
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
