• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.56-67
• /
• 2019

The aim of this study is to develop Artificial Intelligence (AI) based business models of media firms. We define AI and discuss 'AI activity model'. The practices of the efficiency model are home equipment-based personalization and media content recommendation. The practices of the expert model are media content commissioning, content rights negotiation, copyright infringement, and promotion. The practices of the effectiveness model are photo & video auto-tagging and auto subtitling & simultaneous translation. The practices of the innovation model are content script creation and metadata management. The related use cases from 2012 to 2017 are introduced along the four activity models of AI. In conclusion, we propose for media companies to fully utilize the AI for transforming from traditional to successful digital media firms.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2017년도 춘계 종합학술대회 논문집
• /
• pp.453-454
• /
• 2017

The travellers using social media leave their location history in the form of trajectories. These trajectories can be bridged for acquiring information, required for future recommendation for the future travelers, who are new to that location, providing all sort of information. In this paper, we propose a personalized travel path recommendation scheme based on social life log. By taking advantage of two kinds of social media such as travelogue and community contributed photos, the proposed scheme can not only be personalized to user's travel interest but also be able to recommend a travel path rather than individual Points of Interest (POIs). It also maps both user's and routes' textual descriptions to the topical package space to get user topical package model and route topical package model (i.e., topical interest, cost, time and season).

• 인터넷정보학회논문지
• /
• 제16권6호
• /
• pp.133-141
• /
• 2015

소셜 네트워크를 비롯해 다양한 소셜 미디어 서비스들에서 대량의 멀티미디어 콘텐츠들이 공유되고 있다. 소셜 네트워크에는 사용자의 현재 상황과 관심사가 드러나기 때문에 이러한 특징들을 추천시스템에 적용한다면 만족도가 높은 개인화된 추천이 가능할 것이다. 또한 음악을 감정에 따라 분류하고 사용자의 소셜 네트워크를 분석해 사용자가 최근 느끼고 있는 감정이나 현재 상황에 대해 분석한 정보를 이용한다면 사용자의 음악을 추천할 때에 유용할 것이다. 본 논문에서는 음악을 분류하기 위한 감정 모델을 만들고, 감정모델에 따라 음악을 분류하여 소셜 네트워크에 나타나는 사용자의 현재 감정 상태를 추출하여 음악추천을 하는 방법을 제안하고 실험을 통해 제안한 방법의 유효성을 검증한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.389-392
• /
• 2020

The growth in social media, blogs and restaurant listing directories have led to increasing customer reviews about restaurants, their quality of food items and services available on the internet. These user reviews offer a massive amount of valuable information that can be used for various decision-making purposes. Currently, most food recommendation sites provide recommendation scores about restaurants rather than food items of the restaurant and the provided recommendation scores may be biased since they are calculated only from user reviews listed only in their sites. Usually, people wants a reliable recommendation about foods, not restaurant. In this paper, we present a reliable Korean food items rating method; we first extract food items by applying NER technique to restaurant reviews collected from many Korean restaurant recommendation web sites, blogs and web data. Then, we apply lexicon-based sentiment analysis on collected user reviews and predict people's opinions as sentiment polarity scores (+1 for positive; -1 for negative; 0 for neutral). Finally, by taking average of all calculated polarity scores about a food item, we obtain a rating to individual menu items of the restaurant. The proposed food item rating is more reliable since it does not depend on reviews of only one site.

• ETRI Journal
• /
• 제29권3호
• /
• pp.311-321
• /
• 2007

In this paper, we propose a user-centric conflict management method for media services which exploits personal companions for the harmonious detection and resolution of service conflicts. To detect conflicts based on the varying characteristics of individual users, the proposed method exploits the unified context describing all users attempting to access media services. It recommends and mediates users' preferred media contents through a shared screen and personal companions to resolve the detected conflicts. During the recommendation, a list of preferred media contents is displayed on the shared screen, and a personally preferred content list is shown on the user's personal companion comprising the selection of media contents. Mediation assists the selection of a consensual service by gathering the users' selections and highlighting the common media contents. In experiments carried out in a ubiHome, we observed that recommendations and mediation are useful in harmoniously resolving conflicts by encouraging user participation in conflict situations.

• 한국융합학회논문지
• /
• 제13권3호
• /
• pp.133-146
• /
• 2022

전 세계의 인터넷 사용자들이 매일 유튜브를 시청하지만, 검색결과에 대한 추천 알고리즘을 정확히 인지하는 이용자는 극히 드물며, 구글과 유튜브는 이를 공개하지 않고 있다. 연구자들은 공개되어 있지 않은 유튜브의 알고리즘을 역공학설계 방식으로 탐색하고, 핵심적 요인을 찾아 미디어 플랫폼 사업자들이 어떤 논리적 구조로 키워드 검색결과를 추천하고, 화면에 배열하는지 확인하고자 하였다. 따라서 연구자들은 수개월에 걸친 논의와 데이터의 수집을 통해 기초적인 콘텐츠 우선순위 요인을 연구하였으며 수집된 키워드 검색 결과 중에 남, 여 성별에 따른 추천결과를 토대로 영향 요인을 역설계하고자 하였다. 비록 연구자들의 설계는 매시간 수백시간 이상 업로드되고 시청되는 거의 무한한 수준의 데이터 중에서 일부를 분석한 것에 그치지 않지만, 이러한 탐색적 시도가 향후 미디어 플랫폼 알고리즘을 연구하고, 사업자들의 의도를 파악하며, 사용자를 보호할 수 있을 것으로 보았다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.277-280
• /
• 2021

최근 높은 접근성을 기반으로 다양한 콘텐츠가 양산됨에 따라 미디어 콘텐츠 시장이 더욱 활성화되고 있다. 사용자들은 취향에 맞는 콘텐츠를 찾고자 하며, 각 플랫폼에서 콘텐츠의 개인화 추천을 위해 경쟁하고 있다. 효율적인 추천시스템을 위해서는 양질의 메타데이터가 필요하다. 기존의 플랫폼들은 영상의 메타데이터를 사용자가 직접 입력하는 방식을 취하고 있다. 이는 많은 양의 데이터를 처리하는 데에 시간과 비용을 낭비하게 할 것이다. 본 논문에서는 미디어 초개인화 추천을 위해서 영화예고편을 바탕으로, 영상의 YCrCb 컬러 모델을 기반으로 키프레임을 추출하고, 인공지능의 지도학습을 통해 영화 장르를 구별하고 추후 메타데이터 생성을 위한 활용방안을 제안하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제19권11호
• /
• pp.1878-1890
• /
• 2016

Web 2.0 has features produced the content through the user of the participation and share. The content production activities have became active since social network service appear. The social bookmark, one of social network service, is service that lets users to store useful content and share bookmarked contents between personal users. Unlike Internet search engines such as Google and Naver, the content stored on social bookmark is searched based on tag keyword information and unnecessary information can be excluded. Social bookmark can make users access to selected content. However, quick access to content that users want is difficult job because of the user of the participation and share. Our paper suggests a method recommending search word to be able to access quickly to content. A method is suggested by using Collaborative Filtering and Jaccard similarity coefficient. The performance of suggested system is verified with experiments that compare by 'Delicious' and "Feeltering' with our system.

• 지식경영연구
• /
• 제20권2호
• /
• pp.87-103
• /
• 2019

The purpose of this study was to explore the factors influencing acceptance (e.g., comprehension,) and diffusion of information recipients' by depending on the authenticity of news. Specifically, this study has examined the effects of the news contents(political vs. general), need for cognition(high vs. low) and authenticity of the News(real news vs. fake news) on both acceptance and diffusion of news. Based on previous work, this study has developed a conceptual model to present each research hypothesis and tested it by conducting experiments as the follows. As a result, according to the authenticity of the news and the contents of the news (political and general), the acceptance of political contents was high regardless of the authenticity of the news, and the acceptance of real news was higher than that of fake news. However, in the proliferation (comment), both the political contents and the general contents showed the characteristic of spreading (commenting) fake news rather than real news. contrary to this, the cognitive level did not show any significant difference in acceptance (understanding) and proliferation (comment, sharing, recommendation). This study provides academic implications in that it examines the influences of accepting (comprehension) and diffusion (comment, sharing, recommendation) of real news and fake news. It also provides practical implications for responding to fake news and new marketing strategies in an environment where contents are delivered through diverse social media.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1403-1417
• /
• 2019

With the rapid growth of multimedia data, research on cross-media feature learning has significance in many applications, such as multimedia search and recommendation. Existing methods are sensitive to noise and edge information in multimedia data. In this paper, we propose a semi-supervised method for cross-media feature learning by means of $L_{2,q}$ norm to improve the performance of cross-media retrieval, which is more robust and efficient than the previous ones. In our method, noise and edge information have less effect on the results of cross-media retrieval and the dynamic patch information of multimedia data is employed to increase the accuracy of cross-media retrieval. Our method can reduce the interference of noise and edge information and achieve fast convergence. Extensive experiments on the XMedia dataset illustrate that our method has better performance than the state-of-the-art methods.