• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.407-420
• /
• 2019

The purpose of this study is to explore the possibility of measuring advertising effectiveness through the ad evaluation text. The 384 university students were asked to evaluate the positive and negative evaluation ads of high and low involvement products by self-report method and to write ad evaluation text online. The written ad evaluation text were analyzed by KLIWC and to examine the difference between the comment of positive and negative advertising. The results of the analysis are as follows. First, there were differences between positive and negative ads in 17 psychosocial variables. Second, there were differences between positive and negative ads in 9 linguistic variables. Third, there was a significant correlation between KLIWC variables(Positive & negative emotions, inhibition, conviction, physical condition & function and sleep/dreams) and advertising effect variables. This study suggests that the advertising evaluation comment reflects the consumer's psychological reaction to advertising and the possibility of measuring the advertising effectiveness using advertising evaluation text.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.5
• /
• pp.1373-1387
• /
• 2012

Contextual advertising is an important revenue source for major service providers on the Web. Ads classification is one of main tasks in contextual advertising, and it is used to retrieve semantically relevant ads with respect to the content of web pages. However, it is difficult for traditional text classification methods to achieve satisfactory performance in ads classification due to scarce term features in ads. In this paper, we propose a novel ads classification method that handles the lack of term features for classifying ads with short text. The proposed method utilizes a vocabulary expansion technique using semantic associations among terms learned from large-scale search query logs. The evaluation results show that our methodology achieves 4.0% ~ 9.7% improvements in terms of the hierarchical f-measure over the baseline classifiers without vocabulary expansion.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.87-93
• /
• 2015

Advertisements in modern era are not intended to be consumed only as commercial purposes, but consumed also as cultural and artistic purposes. Advertising contents' success depends on Semiotic codes revealed in advertising texts. Advertising scholar Ozoh (1998) argued that perspectives for advertising are divided into two perspective, one as marketing tool perspective and the other as communication processes perspective. Advertising planning, advertising management, advertising, and advertising evaluation of marketing perspective are significantly different from those of communication perspective. Two perspectives of advertising present various debates on what contents of advertising messages are and how advertising messages are made up. In this research manuscripts, we discuss story telling as communication tool of advertising text in terms of cultural semiotics. That is, meaning value of goods is so well revealed in use value of goods that they satisfy consumers' needs, we analyze how they satisfy consumers' needs in semiotic(symbolic) process. We apply Gremas's semantic model to coffee advertisements in France and Korea, and analyze various differences between differentiation strategies of French coffee advertisements and those of Korean coffee advertisements in terms of semiotic perspective.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.19-31
• /
• 2023

The importance of barrier free is being highlighted worldwide. This study attempted to identify barrier-free research trends using text mining. Through this, it was intended to help with research and policies to create a barrier free environment. The analysis data is 227 papers published in domestic academic journals from 1996 when barrier free research began to 2022. The researcher converted the title, keywords, and abstract of an academic thesis into text, and then analyzed the pattern of the thesis and the meaning of the data. The summary of the research results is as follows. First, barrier-free research began to increase after 2009, with an annual average of 17.1 papers being published. This is related to the implementation guidelines for the barrier-free certification system that took effect on July 15, 2008. Second, results of barrier-free text mining i) As a result of word frequency analysis of top keywords, important keywords such as barrier free, disabled, design, universal design, access, elderly, certification, improvement, evaluation, and space, facility, and environment were searched. ii) As a result of TD-IDF analysis, the main keywords were universal design, design, certification, house, access, elderly, installation, disabled, park, evaluation, architecture, and space. iii) As a result of N-Ggam analysis, barrier free+certification, barrier free+design, barrier free+barrier free, elderly+disabled, disabled+elderly, disabled+convenience facilities, the disabled+the elderly, society+the elderly, convenience facilities+installation, certification+evaluation index, physical+environment, life+quality, etc. appeared in a related language. Third, as a result of the CONCOR analysis, cluster 1 was barrier-free issues and challenges, cluster 2 was universal design and space utilization, cluster 3 was Improving Accessibility for the Disabled, and cluster 4 was barrier free certification and evaluation. Based on the analysis results, this study presented policy implications for vitalizing barrier-free research and establishing a desirable barrier free environment.