On the Approximation of Shortest Common Supersequences and Longest Common Subsequences
ICALP '94 Proceedings of the 21st International Colloquium on Automata, Languages and Programming
Mining and summarizing customer reviews
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
NewsInEssence: summarizing online news topics
Communications of the ACM - The digital society
Complementary information retrieval for cross-media news content
Information Systems
Tracking and summarizing news on a daily basis with Columbia's Newsblaster
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Opinion Mining and Sentiment Analysis
Foundations and Trends in Information Retrieval
NewsCube: delivering multiple aspects of news to mitigate media bias
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Finding Comparative Facts and Aspects for Judging the Credibility of Uncertain Facts
WISE '09 Proceedings of the 10th International Conference on Web Information Systems Engineering
A cross-media method of stakeholder extraction for news contents analysis
WAIM'10 Proceedings of the 11th international conference on Web-age information management
ImageAlert: credibility analysis of text-image pairs on the web
Proceedings of the 2011 ACM Symposium on Applied Computing
Says who?: automatic text-based content analysis of television news
Proceedings of the 2013 international workshop on Mining unstructured big data using natural language processing
| Hi-index | 0.00 |
To detect subjective intentions in a multimedia news item and help users avoid the misleading, we propose a Material-Opinion model for ranking the multimedia news with a credibility score. In the model, material is the visual description of the video news. Opinion consists of the subjective words extracted from the surrounding text (or closed captions) of that video news. After extracting materials and opinions from multimedia news items, we compare any two news items to compute their material and opinion dissimilarities, respectively. By considering the support relationship between material and opinion, we compute a credibility score for each multimedia news item. Intuitively, the credibility score of a video news item consists of material and opinion credibility scores. In the event, material credibility score is computed based on the idea that high credible material should be used in most items and they support similar opinions. On the other hand, the idea of computing opinion credibility score is that high credible opinion should be claimed in most news items by using different materials. In this paper, we also present the experiment results that validate our methods.