Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "sentiment" wg kryterium: Temat


Tytuł:
Building sentiment lexicons based on recommending services for the Polish language
Autorzy:
Gliwa, B.
Zygmunt, A.
Dąbrowski, M.
Powiązania:
https://bibliotekanauki.pl/articles/305732.pdf
Data publikacji:
2016
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
sentiment analysis
sentiment lexicons
polarity lexicons
sentiment classification
Opis:
Sentiment analysis has become a prominent area of research in computer science. It has numerous practical applications; e.g., evaluating customer satisfaction, identifying product promoters. Many methods employed in this task require language resources such as sentiment lexicons, which are unavailable for the Polish language. Such lexicons contain words annotated with their emotional polarization, but the manual creation of sentiment lexicons is very tedious. Therefore, this paper addresses this issue and describes a new method of building sentiment lexicons automatically based on recommending services. Next, the built lexicons were used in the task of sentiment classification.
Źródło:
Computer Science; 2016, 17 (2); 163-185
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Towards Application of Speech Act Theory to Opinion Mining
Autorzy:
Pluwak, Agnieszka Magdalena
Powiązania:
https://bibliotekanauki.pl/articles/677344.pdf
Data publikacji:
2016
Wydawca:
Polska Akademia Nauk. Instytut Slawistyki PAN
Tematy:
sentiment analysis
implicit sentiment
speech acts
Opis:
Towards the Application of Speech Act Theory to Opinion MiningThe paper refers to the pragmatics’ perspective on opinion mining in Polish and English, inspired by the discrepancy between the coverage of sentiment analysis and the market demand. An analysis of speech acts expressed in opinion texts reveals that almost half of all opinions include ways of indirect evaluation that might not get extracted while applying traditional methods of sentiment analysis based on direct evaluative vocabulary and polarity lexicons. Coding of sentiment with respect to speech acts could vastly broaden data mining results within an NLP-system. O zastosowaniu teorii aktów mowy w ekstrakcji danych z tekstów opinii internetowychJedno z aktualnych zagadnień językoznawstwa komputerowego, jakim jest automatyczne badanie wydźwięku wypowiedzi, nie uwzględniło dotychczas w wystarczającym stopniu pragmatyki językoznawczej, np. aktów mowy Austina (1961) i Searla (1969), a zatem również implicytnych sposobów wyrażania ewaluacji. Tymczasem podejście od pragmatyki ku konstrukcjom przełożonym na reguły programistyczne umożliwiłoby nie tylko szersze spojrzenie na analizę sentymentu, ale też zbliżyłoby automat do sposobu, w jaki odbiera go człowiek. W szczególności chodzi tu sposoby wyrażania (nie)zadowolenia wykraczające poza poziom leksykalny (bez nacechowanej negatywnie leksyki), typu Nigdy więcej tam nie pójdę.Artykuł prezentuje: 1. aktualne podejścia do analizy wydźwięku w lingwistyce komputerowej, 2. propozycję zastosowania podejścia pragmatycznego, 3. wyniki badania próbki tekstów opinii internetowych pod kątem występowania w nich aktów mowy, 4. propozycję utworzenia reguł ekstrakcji danych na ich podstawie. Zaprezentowane podejście zakłada hipotezę wtórnej oralności, czyli tego, że język opinii jest zapisanym językiem mówionym.
Źródło:
Cognitive Studies; 2016, 16
2392-2397
Pojawia się w:
Cognitive Studies
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Sentiment Analysis of German Texts in Finance: Improving and Testing the BPW Dictionary
Autorzy:
Pöferlein, Matthias
Powiązania:
https://bibliotekanauki.pl/articles/2048284.pdf
Data publikacji:
2021-12-20
Wydawca:
Uniwersytet Warszawski. Wydawnictwo Naukowe Wydziału Zarządzania
Tematy:
textual analysis
textual sentiment
sentiment analysis
content analysis
CEO speeches
annual general meeting
Opis:
Using the dictionary-based approach to measure the sentiment of finance-related texts is primarily focused on English-speaking content. This is due to the need for domain-specific dictionaries and the primary availability of those in English. Through the contribution of Bannier et al. (2019b), the first finance-related dictionary is available for the German language. Because of the novelty of this dictionary, this paper proposes several reforms and extensions of the original word lists. Additionally, I tested multiple measurements of sentiment. I show that using the edited and extended dictionary to calculate a relative measurement of sentiment, central assumptions regarding textual analysis can be fulfilled and more significant relations between the sentiment of a speech by a CEO at the Annual General Meeting and subsequent abnormal stock returns can be calculated.
Źródło:
Journal of Banking and Financial Economics; 2021, 2(16); 5-24
2353-6845
Pojawia się w:
Journal of Banking and Financial Economics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The influence of investor sentiment on sector indices – the INI index analysis
Autorzy:
Rutkowska, Aleksandra
Powiązania:
https://bibliotekanauki.pl/articles/583295.pdf
Data publikacji:
2017
Wydawca:
Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Tematy:
investor sentiment
sector indices
VAR
Opis:
In this paper, we examine the influence of investor sentiment on the WSE sector indices. The stock market indices chosen are based on the industry sector, to distinguish the sectors most susceptible and robust to the effects of sentiment. The Polish Investor Sentiment Index (INI) is used as a sentiment measurement. INI is published every week by the Polish Association of Individual Investors based on the opinions of approx. 350 respondents. Individual investors answer the question about their opinion on the stock exchange trend in the next 6 months, whether the trend will be upward, horizontal, or downward. The aim of this study is to understand the impact of investor sentiment on sector indices. The study covers the 5-year period from June 2011 to June 2016. We examine the bivariate relationship in the mean by using the vector autoregression (VAR) model and Granger causality. The results show that INI does not influence the sector indices except for WIG-food and WIG-basic materials. However, the study identifies strong dependencies in the opposite direction.
Źródło:
Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu; 2017, 482; 227-239
1899-3192
Pojawia się w:
Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Applicability of the Multi- Group Confirmatory Factor Analysis to Construction of Business Sentiment Indicators
Zastosowanie konfirmacyjnej analizy czynnikowej dla wielu grup do tworzenia wskaźników koniunktury
Autorzy:
Białowolski, Piotr
Powiązania:
https://bibliotekanauki.pl/articles/906852.pdf
Data publikacji:
2012
Wydawca:
Uniwersytet Łódzki. Wydawnictwo Uniwersytetu Łódzkiego
Tematy:
Confirmatory Factor Analysis
Sentiment Indicators
Opis:
The paper presents arguments that advocate for application of the multi-group confirmatory factor analysis as a tool for constructing sentiment indicators in business surveys. Reliable measurement and comparisons of the sentiment mean between periods require measurement invariance on its three basic levels-configural, metric and scalar invariance. It is hypothesized that only sets of questions that are internally coherent can serve as a group of proxies for business sentiment indicator. An attempt to construct two different sentiment indicators for manufacturing industry is performed. The results show that only for the set of coherent proxies it is possible to estimate model with measurement invariance.
Źródło:
Acta Universitatis Lodziensis. Folia Oeconomica; 2012, 269
0208-6018
2353-7663
Pojawia się w:
Acta Universitatis Lodziensis. Folia Oeconomica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Interdependence of sentiment indicators − a case of the Polish OTC market
Autorzy:
Jaworski, Piotr
Mielus, Piotr
Powiązania:
https://bibliotekanauki.pl/articles/949757.pdf
Data publikacji:
2017
Wydawca:
Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Tematy:
emerging markets
market sentiment
cointegration analysis
Opis:
Prices observed on emerging markets are affected by market sentiment changes. The article presents an interdependence analysis of a chosen set of sentiment indicators observed on the Polish OTC market. The set contains both interest rate market (basis swap, asset swap, convergence swap, overnight index swap), foreign exchange market (ATM volatility, risk reversal) and equity market (WIG20). The analysis is focused on cointegration and Granger causality approach in order to present forecasting power of elaborated models. Evidence from the market reveals economic link between the time series that comes from the strong influence of the cross-border trading between non-residents and local market makers. High responsiveness of daily prices of OTC instruments to the changes of the market sentiment and a level of the risk aversion can be proven. Moreover, error correction model using foreign exchange options has practical forecasting power generating adequate trading decisions taken by market makers
Źródło:
Financial Sciences. Nauki o Finansach; 2017, 2(31); 31-43
2080-5993
2449-9811
Pojawia się w:
Financial Sciences. Nauki o Finansach
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Effect of service quality assessment on perception of TOP hotels in terms of sentiment polarity in the Visegrad group countries
Autorzy:
Stefko, Robert
Fedorko, Richard
Bacik, Radovan
Rigelsky, Martin
Olearova, Maria
Powiązania:
https://bibliotekanauki.pl/articles/19233601.pdf
Data publikacji:
2020
Wydawca:
Instytut Badań Gospodarczych
Tematy:
sentiment polarity
customer satisfaction
hotel
Visegrad group
Opis:
Research background: In the developed countries, the services sector, which also includes the accommodation services, is a significant source of the gross national product. Tourism can be perceived as an important determinant of countries' economies, so attention paid to the needs of clients is at least necessary and beneficial. Purpose of the article: The aim of the study is to assess the quality of services provided and the perception of the hotel from the point of view of the accommodated clients. This objective was fulfilled by determining the effect of selected indicators of perception of the quality of provided services (location, personnel evaluation, cleanliness, equipment, comfort, price/quality ratio of provided services, free Wi-Fi connection) on the indicator determining the perception of the hotel (polarity of sentiment). Methods: In the analysis of the above, 22,000 text-reviews of 117 five-star hotels of the Visegrad Group countries were evaluated. The hotel reviews were obtained from Tripadvisor.com and indicator rankings from Booking.com. The analysis made use of the regression analysis methods - influence (regulatory models - Ridge, Lasso, Elastic net, and multiple linear regression - OLS). Findings & Value added: It has been found out that hotel equipment and cleanliness have the greatest effect on the polarity of sentiment. As could be expected, the trend has an upward tendency - that is, as quality increases, so does the sentiment polarity - the perception of hotel facilities. Overall, the analysed sentiment variables can be considered positive, as was confirmed by the positive coefficients of the coherence analysis (Spearman-ρ; Pearson-r), as well as the upward trend in the predictions under the regression analysis. Hotels should be strategically customer-oriented and, as the analyses show, pay the greatest attention to equipment and cleanliness. The services of accommodation facilities are dominant in terms of satisfaction with the destination in general, so in the long run, they should be given due attention. These findings are particularly beneficial for hotel services provided in the Visegrad Group countries, as no research studies have yet been carried out on customer evaluation of the quality of accommodation facilities using the presented methods.
Źródło:
Oeconomia Copernicana; 2020, 11, 4; 721-742
2083-1277
Pojawia się w:
Oeconomia Copernicana
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Comparison of Poznań, Wrocław and Bratislava Image Attributes in the Reviews Published on TripAdvisor
Autorzy:
Nowacki, Marek
Niezgoda, Agnieszka
Powiązania:
https://bibliotekanauki.pl/articles/1391022.pdf
Data publikacji:
2019
Wydawca:
Wyższa Szkoła Bankowa w Poznaniu
Tematy:
image
cities
attributes
sentiment analysis
correspondence analysis
Opis:
The aim of the article is to identify unique image attributes of Poznań, Wrocław and Bratislava. It was made using the analysis of opinions posted on the English-language TripAdvisor website (‘Things to do…’ category for three cities). 76 most-emerging words-attributes were extracted from 29,383 reviews with the text mining procedure. These words differentiate the examined cities among themselves. Analysis of the correspondence revealed unique image attributes for each city. In addition, sentiment analysis was carried out, which showed differences in the affective dimension of the images between the cities.
Źródło:
Studia Periegetica; 2019, 26(2); 63-77
1897-9262
2658-1736
Pojawia się w:
Studia Periegetica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analysis of Factors Influencing Developers Sentiments in Commit Logs: Insights from Applying Sentiment Analysis
Autorzy:
Kaur, Rajdeep
Chahal, Kuljit Kaur
Saini, Munish
Powiązania:
https://bibliotekanauki.pl/articles/2123250.pdf
Data publikacji:
2022
Wydawca:
Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Tematy:
human factor
software development team
software developer
developers' sentiment
sentiment analysis
commit log
developer activity type
team size
Opis:
Background: In the open source software paradigm, software development depends upon efforts of volunteer members that are geographically dispersed and collaborate with each other over the Internet. Communication artifacts like mailing lists, forums, and issue tracking systems are used by developers for communication. The way they express themselves through these communication channels greatly influences their productivity, efficiency of development activities, and survival of the project as well. Therefore, it is essential to understand affective state of developers’ contributions to make software engineering more effective. Aim: This study examined commit logs of seven GitHub projects to analyze developers’ sentiments. This study also investigated the relationship of developers’ sentiments in commit logs with team size of project, type of change activity, and contribution volume. Method: Sentiments of developers are calculated using SentiStrength-SE tool that is specialized in software engineering domain. Results: Our findings revealed that the majority of sentiments conveyed by developers in commit logs were neutral. Furthermore, we found that team size, change activity, and commit contribution volume influenced sentiments conveyed in commit logs. Conclusion: Our findings will help project managers to better understand developer sentiments while performing different software development tasks/activities. It will be beneficial in improving developer productivity and retention.
Źródło:
e-Informatica Software Engineering Journal; 2022, 16, 1; art. no. 220102
1897-7979
Pojawia się w:
e-Informatica Software Engineering Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Z badań nad systemem rafinacji sieciowej. Identyfikacja sentymentów
From research on the system of refining the Web. Identifying sentiment words
Autorzy:
Gogołek, Włodzimierz
Jaruga, Dariusz
Powiązania:
https://bibliotekanauki.pl/articles/1288721.pdf
Data publikacji:
2016
Wydawca:
Uniwersytet Warszawski. Wydział Dziennikarstwa, Informacji i Bibliologii
Tematy:
informacja
internet
Big Data
kolekcjonowanie informacji
identyfikacja sentymentów
analiza sentymentów
information
collecting information
identifying sentiment words
sentiment analysis
Opis:
Dostępny potencjał mocy obliczeniowych i pamięci komputerowych stworzył niedostępne wcześniej warunki do analizy dużych zasobów informacyjnych – Big Data. W procesie tej analizy można wykorzystywać procedury kolekcjonowania informacji i ich analizy do trafnej oceny – w kategoriach emocjonalnych (sentymentów – dobry, zły) badanych zjawisk w przeszłości, w czasie rzeczywistym, a także do predykcji. Artykuł jest prezentacją kluczowej części tej procedury – istoty automatyzacji procesu identyfikacji sentymentów.
Available potential of computing power and computer memory had created, previously unavailable conditions for the analysis of, large information resources – Big Data. In the process of this analysis can be used procedures for collecting information and analysis for the accurate assessment – in terms of emotional (sentiments – good, bad) of studied phenomena – in the past, in real time, as well as to the prediction. The article is a presentation of the key parts of this procedure – being automate the process of identifying sentiment words.
Źródło:
Studia Medioznawcze; 2016, 4 (67); 103-111
2451-1617
Pojawia się w:
Studia Medioznawcze
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Adapting a constituency parser to user-generated content in polish opinion mining
Autorzy:
Pluwak, A.
Korczynski, W.
Kisiel-Dorohinicki, M.
Powiązania:
https://bibliotekanauki.pl/articles/305485.pdf
Data publikacji:
2016
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
user generated content
text normalization
parsing
sentiment analysis
Opis:
The paper focuses on the adjustment of NLP tools for Polish; e.g., morphological analyzers and parsers, to user-generated content (UGC). The authors discuss two rule-based techniques applied to improve their efficiency: pre-processing (text normalization) and parser adaptation (modified segmentation and parsing rules). A new solution to handle OOVs based on inflectional translation is also offered.
Źródło:
Computer Science; 2016, 17 (1); 23-44
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An environment for collective perception based on fuzzy and semantic approaches
Autorzy:
D’Aniello, G.
Gaeta, M.
Loia, F.
Reformat, M.
Toti, D.
Powiązania:
https://bibliotekanauki.pl/articles/91892.pdf
Data publikacji:
2018
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
smart cities
fuzzy logic
text mining
sentiment analysis
Opis:
This work proposes a software environment implementing a methodology for acquiring and exploiting the collective perception (CP) of Points of Interests (POIs) in a Smart City, which is meant to support decision makers in urban planning and management. This environment relies upon semantic knowledge discovery techniques and fuzzy computational approaches, including natural language processing, sentiment analysis, POI signatures and Fuzzy Cognitive Maps, turning them into a cohesive architectural blend in order to effectively gather the realistic perception of a user community towards given areas and attractions of a Smart City. The environment has been put to the test via a thorough experimentation against a massive user base of an online community with respect to a large metropolitan city (the City of Naples). Such an experimentation yielded consistent results, useful for providing decision makers with a clear awareness of the positive as well as critical aspects of urban areas, and thus helping them shape the measures to be taken for an improved city management and development.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2018, 8, 3; 191-210
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Post-development sentiment and statistical analysis of different groups of psychiatric medications
Autorzy:
Ghassemi Toosi, Farshad
Ghassemi Toussi, Alireza
Powiązania:
https://bibliotekanauki.pl/articles/33894821.pdf
Data publikacji:
2024-06-25
Wydawca:
Gdański Uniwersytet Medyczny
Tematy:
anxiety
clinical trials
SSRIs
sentiment analysis
psychiatric medication
Opis:
Background Post-development analysis of medications allows for comprehensive understanding of the safety profile over extended periods, and can direct future improvements to enhance the therapeutic benefits while minimizing risks. Our primary goal was to examine whether a substantial relationship exists between such patient experiences and the statistical analysis of data about the same medications from clinical trials. Material and methods Patient feedback regarding medication commonly prescribed for psychiatric conditions was obtained from a publicly available website webmd.com. We searched clinicaltrials.gov for statistical analysis regarding the same medications. Data from webmd.com was subjected to sentiment analysis, while ClinicalTrials data underwent statistical analysis. Results The findings suggest a general connection between the two data sources. Medications with a greater amount of patient feedback generally attract more research attention, although with some exceptions. Additionally, medications approved for children receive less feedback online compared to those for adults and seniors. Medications for seniors receive more positive and neutral feedback in contrast to those for children and adults. Conclusions Online platforms offer a space for patients to share their experiences with using specific medications, potentially contributing to the enhancement of patient care and aiding researchers in further studies.
Źródło:
European Journal of Translational and Clinical Medicine; 2024, 7, 1; 47-56
2657-3148
2657-3156
Pojawia się w:
European Journal of Translational and Clinical Medicine
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Wahania koniunkturalne w województwie lubelskim
Business Cycle Fluctuations in Poland’s Lublin Region
Autorzy:
Kowerski, Mieczysław
Powiązania:
https://bibliotekanauki.pl/articles/575548.pdf
Data publikacji:
2009-08-31
Wydawca:
Szkoła Główna Handlowa w Warszawie. Kolegium Analiz Ekonomicznych
Tematy:
Lublin region
business cycle
business sentiment
slowdown
recession
Opis:
The paper examines business cycles in Poland’s Lublin province using quarterly business sentiment indicators calculated since the second quarter of 2001. Both composite and sector indicators are calculated on the basis of the results of quarterly surveys covering 320 companies and 350 households. Sector indicators are calculated as weighted arithmetic means of respondents’ assessment of their current condition and forecasts for the next quarter. Composite indicators are weighted averages of sector indicators, with the shares of individual sectors in gross value added generated in the province used as weights. Industry and construction in Lublin province began to slow down in the second quarter of 2007, according to Kowerski. By now the slowdown in these sectors has become evident. The slump in the service sector began in the first quarter of 2008, and consumers felt the downturn in the second quarter of 2008. The retail sector has yet to experience a downturn, according to Kowerski. The composite indicator of business sentiment began to deteriorate markedly in the second quarter of 2008. The research shows that the economy of the Lublin region began to slow down in the first half of 2008, though it is unclear if this trend can be called a recession, the author says.
Źródło:
Gospodarka Narodowa. The Polish Journal of Economics; 2009, 233, 7-8; 93-106
2300-5238
Pojawia się w:
Gospodarka Narodowa. The Polish Journal of Economics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Can Google Trends affect sentiment of individual investors? The case of the United States
Autorzy:
Rutkowska, Aleksandra
Kliber, Agata
Powiązania:
https://bibliotekanauki.pl/articles/584982.pdf
Data publikacji:
2018
Wydawca:
Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Tematy:
investor sentiment
GARCH models
behavioural finance
Google Trends
Opis:
As the empirical studies show, investor sentiment is a significant factor in financial markets. The large-scale development of the technology has led to widespread access to information in real time (also to individual investors), which in turn has also led to the inflow of Big Data to market analysis. One of the sources of such data is the ability to track the phrases searched for in the web search engines. In our research we verify whether investor sentiment is affected by, among others, a daily Google keyword search called “Google Trends”. We consider measures of US investors’ sentiment calculated from survey studies – the AAII index. We investigate changes of sentiment and its volatility, which can be interpreted as nervousness of the market participants. We estimate a set of GARCH models with explanatory variables in conditional mean and variance. We confirm that negative keyword searches are connected with the decline of the investor confidence. The overall effect of a negative search is stronger than positive. Older searches have a weaker influence on investor sentiment than new ones – no lagged search proved to be significant.
Źródło:
Mathematical Economics; 2018, 14(21); 51-70
1733-9707
Pojawia się w:
Mathematical Economics
Dostawca treści:
Biblioteka Nauki
Artykuł

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies