Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880178
N. Hanh, Phan Thi Hong Hanh, Huynh Thi Thanh Binh, N. D. Nghia
Wireless sensor networks include a set of sensors being network nodes and a base station. The objective of such systems is to monitor changes which might occur at targets' location. Consequently, assuring the network connectivity is compulsory to maintain a continuous monitoring of given set of targets. However, sensor nodes sometimes stop functioning due to being physically damaged or running out of energy (battery), thus affecting to the connectivity of the system. This paper considers the target coverage with connectivity fault-tolerance problem in wireless sensor networks. The goal of this problem is to come up with a network topology consisting of the least number of sensor nodes that not only offers the greatest target coverage but also maintains the network connectivity even when one random node is defected. This is an NP-Complete combinatorial optimization problem. One heuristic algorithm is proposed to solve the target coverage with connectivity fault-tolerance problem and it is tested on 15 randomly generated instances. Experimental results illustrate a good performance achieved in terms of target coverage, connectivity and fault-tolerance.
{"title":"Heuristic algorithm for target coverage with connectivity fault-tolerance problem in wireless sensor networks","authors":"N. Hanh, Phan Thi Hong Hanh, Huynh Thi Thanh Binh, N. D. Nghia","doi":"10.1109/TAAI.2016.7880178","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880178","url":null,"abstract":"Wireless sensor networks include a set of sensors being network nodes and a base station. The objective of such systems is to monitor changes which might occur at targets' location. Consequently, assuring the network connectivity is compulsory to maintain a continuous monitoring of given set of targets. However, sensor nodes sometimes stop functioning due to being physically damaged or running out of energy (battery), thus affecting to the connectivity of the system. This paper considers the target coverage with connectivity fault-tolerance problem in wireless sensor networks. The goal of this problem is to come up with a network topology consisting of the least number of sensor nodes that not only offers the greatest target coverage but also maintains the network connectivity even when one random node is defected. This is an NP-Complete combinatorial optimization problem. One heuristic algorithm is proposed to solve the target coverage with connectivity fault-tolerance problem and it is tested on 15 randomly generated instances. Experimental results illustrate a good performance achieved in terms of target coverage, connectivity and fault-tolerance.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115967729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880154
Kiminori Matsuzaki
The puzzle game 2048, a single-player stochastic game played on a 4 × 4 grid, is the most popular among similar slide-and-merge games. One of the strongest computer players for 2048 uses temporal difference learning (TD learning) on so called N-tuple networks, where the shapes of the N-tuples are given by human based on characteristics of the game. In our previous work (Oka and Matsuzaki, 2016), the authors proposed a systematic method of selecting N-tuples under an assumption that the interinfluence among those N-tuple networksn are negligible. Though the selected N-tuple networks worked fine, there were large gaps between those N-tuple networks and the human-designed networks. In this paper, another systematic and game-characteristics-free method of selecting N-tuples is proposed for game 2048, in which the interinfluence among those N-tuple networks is captured. The proposed method is effective and generic: the selected N-tuple networks are as good as human-designed ones under the same setting, and we can obtain larger (or smaller) N-tuple networks in the same manner. We also report the experiment results when we combine the N-tuple networks and expectimax search.
{"title":"Systematic selection of N-tuple networks with consideration of interinfluence for game 2048","authors":"Kiminori Matsuzaki","doi":"10.1109/TAAI.2016.7880154","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880154","url":null,"abstract":"The puzzle game 2048, a single-player stochastic game played on a 4 × 4 grid, is the most popular among similar slide-and-merge games. One of the strongest computer players for 2048 uses temporal difference learning (TD learning) on so called N-tuple networks, where the shapes of the N-tuples are given by human based on characteristics of the game. In our previous work (Oka and Matsuzaki, 2016), the authors proposed a systematic method of selecting N-tuples under an assumption that the interinfluence among those N-tuple networksn are negligible. Though the selected N-tuple networks worked fine, there were large gaps between those N-tuple networks and the human-designed networks. In this paper, another systematic and game-characteristics-free method of selecting N-tuples is proposed for game 2048, in which the interinfluence among those N-tuple networks is captured. The proposed method is effective and generic: the selected N-tuple networks are as good as human-designed ones under the same setting, and we can obtain larger (or smaller) N-tuple networks in the same manner. We also report the experiment results when we combine the N-tuple networks and expectimax search.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120986862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880183
Takuya Masukane, Kazunori Mizuno
To solve large-scale constraint satisfaction problems, CSPs, ant colony optimization, ACO, based meta-heuristics has been effective. However, the naive ACO based method is sometimes inefficient because the method has only single pheromone trails. In this paper, we propose an ant colony optimization based meta-heuristics with multi pheromone trails in which artificial ants construct a candidate assignment by referring several pheromone trail graphs to solve CSP instances. We also implement the proposed model to some ACO based methods, demonstrating how our method is effective for solving graph coloring problems that is one of typical examples of CSPs.
{"title":"Ant colony optimization with multi-pheromones for solving constraint satisfaction problems","authors":"Takuya Masukane, Kazunori Mizuno","doi":"10.1109/TAAI.2016.7880183","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880183","url":null,"abstract":"To solve large-scale constraint satisfaction problems, CSPs, ant colony optimization, ACO, based meta-heuristics has been effective. However, the naive ACO based method is sometimes inefficient because the method has only single pheromone trails. In this paper, we propose an ant colony optimization based meta-heuristics with multi pheromone trails in which artificial ants construct a candidate assignment by referring several pheromone trail graphs to solve CSP instances. We also implement the proposed model to some ACO based methods, demonstrating how our method is effective for solving graph coloring problems that is one of typical examples of CSPs.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121184643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880158
Chetprayoon Panumate, H. Iida, J. Terrillon
This paper introduces a family of RoShamBo games, denoted by RSB(n,b,s,r) which means that n players simultaneously show a move among b possible moves with possible s winning regulations, at each round out of r round matches in total. The player who wins more after r rounds wins. A game informatical analysis of RSB(n,b,s,r) using game refinement measure is carried out, while experiments have been conducted by developing computer players and simulating a million RoShamBo games. Results show that RSB(n, 3, 1, 1) is best to play with n = 8 or 9 and RSB(2, 3, 1,r) is best to play with r = 9 or 10. Moreover, it is confirmed that popular RoShamBo-based games such as GuRiKo in Japan and King PaoYingShub in Thailand have been played with reasonable settings.
{"title":"A game informatical analysis of RoShamBo","authors":"Chetprayoon Panumate, H. Iida, J. Terrillon","doi":"10.1109/TAAI.2016.7880158","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880158","url":null,"abstract":"This paper introduces a family of RoShamBo games, denoted by RSB(n,b,s,r) which means that n players simultaneously show a move among b possible moves with possible s winning regulations, at each round out of r round matches in total. The player who wins more after r rounds wins. A game informatical analysis of RSB(n,b,s,r) using game refinement measure is carried out, while experiments have been conducted by developing computer players and simulating a million RoShamBo games. Results show that RSB(n, 3, 1, 1) is best to play with n = 8 or 9 and RSB(2, 3, 1,r) is best to play with r = 9 or 10. Moreover, it is confirmed that popular RoShamBo-based games such as GuRiKo in Japan and King PaoYingShub in Thailand have been played with reasonable settings.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122842448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880174
Shi Fang, Kaigui Bian, Haikun Hong, Kunqing Xie, Yuwen Fu
The spatial clustering of highway traffic is of great interest to researchers and policy makers. In this paper, instead of using the microscopic traffic parameters in the traditional clustering methods, we introduce a new heterogeneity index clustering the sections of a highway based on differences in the content, a.k.a. “Heterogeneity”, in their flow, which can be used as a universal guideline for network spatial clustering. Using real-world toll station origin to destination (O-D) data in three highway networks of China, we evaluate the stability of the traffic heterogeneity and verify the strong correlation between the traffic heterogeneity and the traffic variation. A case study on the hierarchical clustering for these highway roads was carried out, and we evaluate the clustering performances and show that the heterogeneity is a better partitioning criterion than other conventional traffic indices.
{"title":"Using the traffic heterogeneity of Chinese toll highway networks for hierarchical clustering","authors":"Shi Fang, Kaigui Bian, Haikun Hong, Kunqing Xie, Yuwen Fu","doi":"10.1109/TAAI.2016.7880174","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880174","url":null,"abstract":"The spatial clustering of highway traffic is of great interest to researchers and policy makers. In this paper, instead of using the microscopic traffic parameters in the traditional clustering methods, we introduce a new heterogeneity index clustering the sections of a highway based on differences in the content, a.k.a. “Heterogeneity”, in their flow, which can be used as a universal guideline for network spatial clustering. Using real-world toll station origin to destination (O-D) data in three highway networks of China, we evaluate the stability of the traffic heterogeneity and verify the strong correlation between the traffic heterogeneity and the traffic variation. A case study on the hierarchical clustering for these highway roads was carried out, and we evaluate the clustering performances and show that the heterogeneity is a better partitioning criterion than other conventional traffic indices.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128732234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880176
Yuzana Win, Tomonari Masada
This paper proposes a method for proper names extraction from Myanmar text by using latent Dirichlet allocation (LDA). Our method aims to extract proper names that provide important information on the contents of Myanmar text. Our method consists of two steps. In the first step, we extract topic words from Myanmar news articles by using LDA. In the second step, we make a post-processing, because the resulting topic words contain some noisy words. Our post-processing, first of all, eliminates the topic words whose prefixes are Myanmar digits and suffixes are noun and verb particles. We then remove the duplicate words and discard the topic words that are contained in the existing dictionary. Consequently, we obtain the words as candidate of proper names, namely personal names, geographical names, unique object names, organization names, single event names, and so on. The evaluation is performed both from the subjective and quantitative perspectives. From the subjective perspective, we compare the accuracy of proper names extracted by our method with those extracted by latent semantic indexing (LSI) and rule-based method. It is shown that both LS] and our method can improve the accuracy of those obtained by rule-based method. However, our method can provide more interesting proper names than LSI. From the quantitative perspective, we use the extracted proper names as additional features in K-means clustering. The experimental results show that the document clusters given by our method are better than those given by LSI and rule-based method in precision, recall and F-score.
{"title":"Extraction of proper names from myanmar text using latent dirichlet allocation","authors":"Yuzana Win, Tomonari Masada","doi":"10.1109/TAAI.2016.7880176","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880176","url":null,"abstract":"This paper proposes a method for proper names extraction from Myanmar text by using latent Dirichlet allocation (LDA). Our method aims to extract proper names that provide important information on the contents of Myanmar text. Our method consists of two steps. In the first step, we extract topic words from Myanmar news articles by using LDA. In the second step, we make a post-processing, because the resulting topic words contain some noisy words. Our post-processing, first of all, eliminates the topic words whose prefixes are Myanmar digits and suffixes are noun and verb particles. We then remove the duplicate words and discard the topic words that are contained in the existing dictionary. Consequently, we obtain the words as candidate of proper names, namely personal names, geographical names, unique object names, organization names, single event names, and so on. The evaluation is performed both from the subjective and quantitative perspectives. From the subjective perspective, we compare the accuracy of proper names extracted by our method with those extracted by latent semantic indexing (LSI) and rule-based method. It is shown that both LS] and our method can improve the accuracy of those obtained by rule-based method. However, our method can provide more interesting proper names than LSI. From the quantitative perspective, we use the extracted proper names as additional features in K-means clustering. The experimental results show that the document clusters given by our method are better than those given by LSI and rule-based method in precision, recall and F-score.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115421360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the area of national language processing, performing machine learning technique on customer or movie review for sentiment analysis has been? frequently tried. While methods such as? support vector machine (SVM) were much favored in the 2000s, recently there is a steadily rising percentage of implementation with vector representation and artificial neural network. In this article we present an approach to implement word embedding method to conduct sentiment analysis on movie review from a renowned bulletin board system forum in Taiwan. After performing log-likelihood ratio (LLR) on the corpus and selecting the top 10000 most related keywords as representative vectors for different sentiments, we use these vectors as the sentiment classifier for the testing set. We achieved results that are not only comparable to traditional methods like Naïve Bayes and SVM, but also outperform Latent Dirichlet Allocation, TF-IDF and its variant. It also tops the original LLR with a substantial margin.
{"title":"Sentiment analysis on Chinese movie review with distributed keyword vector representation","authors":"Chun-Han Chu, Chen-Ann Wang, Yung-Chun Chang, Ying-Wei Wu, Yu-Lun Hsieh, W. Hsu","doi":"10.1109/TAAI.2016.7880169","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880169","url":null,"abstract":"In the area of national language processing, performing machine learning technique on customer or movie review for sentiment analysis has been? frequently tried. While methods such as? support vector machine (SVM) were much favored in the 2000s, recently there is a steadily rising percentage of implementation with vector representation and artificial neural network. In this article we present an approach to implement word embedding method to conduct sentiment analysis on movie review from a renowned bulletin board system forum in Taiwan. After performing log-likelihood ratio (LLR) on the corpus and selecting the top 10000 most related keywords as representative vectors for different sentiments, we use these vectors as the sentiment classifier for the testing set. We achieved results that are not only comparable to traditional methods like Naïve Bayes and SVM, but also outperform Latent Dirichlet Allocation, TF-IDF and its variant. It also tops the original LLR with a substantial margin.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128375236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880110
Gerel Tumenbayar, Hung-Yu kao
Since Web 2.0 emerges, users became very active in attending Web forum and Q&A Community. For the community about technology, engineering and science, it is likely that most of the professionals follow the same general path to study specific knowledge and this path would be between topics from basic one to specific one or from topic about old technology to a topic about new technology. Our work aims to find this general conditional relationship between topics by using Bayesian Network model and then use this model to suggest the reasonable topics for professionals to further study.
{"title":"Topic suggestion by Bayesian network enhanced tag inference in community question answering","authors":"Gerel Tumenbayar, Hung-Yu kao","doi":"10.1109/TAAI.2016.7880110","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880110","url":null,"abstract":"Since Web 2.0 emerges, users became very active in attending Web forum and Q&A Community. For the community about technology, engineering and science, it is likely that most of the professionals follow the same general path to study specific knowledge and this path would be between topics from basic one to specific one or from topic about old technology to a topic about new technology. Our work aims to find this general conditional relationship between topics by using Bayesian Network model and then use this model to suggest the reasonable topics for professionals to further study.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134288724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880181
R. Wang, Rui Wang, Chih-Hua Tai, De-Nian Yang
It might not seem dangerous for a person to leave some pieces of personal information on the Internet since everyone tends to do this. But the truth is that if someone ever tries to collect those pieces of information together, he might be able to find out the true identity of the person in reality after analyzing the collected data, which is what we call “cyber hunting”. This work focuses on the question of “what kind(s) of personal information will lead to a higher risk of personal re-identification on the Internet?” To answer this question, we conducted a case study of PTT-and-FB linkage and share effective suggestions for Internet users to avoid being cyber hunted. At the end of this work, we found that the three attributes of gender, birthday and location are more sensitive compared to other attributes and users should prevent themselves from providing these kinds of information to secure their privacy.
{"title":"Sensitive information for privacy on social networks a case study of PTT-and-FB linkage","authors":"R. Wang, Rui Wang, Chih-Hua Tai, De-Nian Yang","doi":"10.1109/TAAI.2016.7880181","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880181","url":null,"abstract":"It might not seem dangerous for a person to leave some pieces of personal information on the Internet since everyone tends to do this. But the truth is that if someone ever tries to collect those pieces of information together, he might be able to find out the true identity of the person in reality after analyzing the collected data, which is what we call “cyber hunting”. This work focuses on the question of “what kind(s) of personal information will lead to a higher risk of personal re-identification on the Internet?” To answer this question, we conducted a case study of PTT-and-FB linkage and share effective suggestions for Internet users to avoid being cyber hunted. At the end of this work, we found that the three attributes of gender, birthday and location are more sensitive compared to other attributes and users should prevent themselves from providing these kinds of information to secure their privacy.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121535814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68% on Berlin dataset, 76% on Youtube data and 73.33% on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.
{"title":"Automatic opinion leader recognition in group discussions","authors":"Yujeung Ho, Hao-Min Liu, Hui-Hsin Hsu, Chun-Han Lin, Yao-Hua Ho, Ling-Jyh Chen","doi":"10.1109/TAAI.2016.7880177","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880177","url":null,"abstract":"In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68% on Berlin dataset, 76% on Youtube data and 73.33% on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129976920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：