Results 61 to 70 of about 6,791 (190)
Automatic Classifying of Requirements-Relevant Contents From App Reviews in the Arabic Language
IEEE Open Journal of the Computer SocietyThe market for mobile application development continues to thrive with billions of users and millions of apps. Collecting software requirements for mobile apps has to cope with this trend, so as for the software to compete in this crowded scene ...
Abualsoud A. Hanani +2 more
doaj +1 more source
DAWE: A Double Attention-Based Word Embedding Model with Sememe Structure Information
Applied Sciences, 2020 Word embedding is an important reference for natural language processing tasks, which can generate distribution presentations of words based on many text data.
Shengwen Li +5 more
doaj +1 more source
Family Control and Ownership, Corporate Culture, and ESG Performance in Thailand
Corporate Social Responsibility and Environmental Management, EarlyView.ABSTRACT Motivated by the growing importance of environmental, social, and governance (ESG) performance in emerging markets, we examine how family control and ownership, together with corporate culture, influence the ESG performance of publicly listed firms in Thailand.
Sirimon Treepongkaruna +2 more
wiley +1 more source
Analysis of the impact of the contextual embeddings usage on the text classification accuracy
Радіоелектронні і комп'ютерні системиAnalysis of the impact of the contextual embeddings usage on the text classification ...
Olesia Barkovska +4 more
doaj +1 more source
Transactions of the Karelian Research Centre of the Russian Academy of Sciences, 2018 The problem of word sense disambiguation (WSD) is considered in the article. Set of synonyms (synsets) and sentences with these synonyms are taken. It is necessary to automatically select the meaning of the word in the sentence.
Andrew Krizhanovsky +2 more
doaj +1 more source
Journal of Applied Toxicology, EarlyView.ABSTRACT Carcinogenicity evaluation is a critical component of chemical risk assessment, yet traditional in vivo testing remains time consuming, costly, and ethically challenging. Computational approaches based on machine learning offer promising alternatives, but the relative contributions of different molecular representation strategies for ...
Iuri Barbosa Pereira +2 more
wiley +1 more source
Strategic Entrepreneurship Journal, EarlyView.Abstract Research Summary Using 14,108 Kickstarter crowdfunding campaigns, we examine three strategies to gather support from first‐time versus repeat backers: narrative distinctiveness aligning with backers' expectations of novelty, endorsement from Kickstarter staff, and campaign leadership's reciprocity of funding other campaigns.
Stephanie Hepp +2 more
wiley +1 more source
IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 2020 Currently, the discussion about hate speech in Indonesia is warm, primarily through social media. Hate speech is communication that disparages a person or group based on characteristics such as (race, ethnicity, gender, citizenship, religion and ...
Auliya Rahman Isnain +2 more
doaj +1 more source
Immune2vec: Embedding B/T Cell Receptor Sequences in ℝN Using Natural Language Processing
Frontiers in Immunology, 2021 The adaptive branch of the immune system learns pathogenic patterns and remembers them for future encounters. It does so through dynamic and diverse repertoires of T- and B- cell receptors (TCR and BCRs, respectively).
Miri Ostrovsky-Berman +7 more
doaj +1 more source
Mixed feelings, mixed outcomes? When emotionally ambivalent framing enhances idea appreciation
Strategic Entrepreneurship Journal, EarlyView.Abstract Research Summary Despite growing interest in how linguistic strategies shape audience responses to innovative ideas, prior evidence on the benefits of using emotional language remains mixed. Building on research on emotional ambivalence and social evaluation, we introduce the concept of emotionally ambivalent framing (i.e., the combination of ...
Donato Cutolo +2 more
wiley +1 more source