Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, differences in user and system terminologies can challenge the identification of the user's information needs, and thus the generation of relevant results. We argue that the explicit management of ontological knowledge, and of the meaning of concepts (by integrating linguistic and encyclopaedic knowledge in the system ontology), can improve the analysis of search queries, because it enables a flexible identification of the topics the user is searching for, regardless of the adopted vocabulary. This paper proposes an information retrieval support model based on semantic concept identification. Starting from the recognition of the ontology concepts that the search query refers to, this model exploits the qualifiers specified in the query to select information items on the basis of possibly fine-grained features. Moreover, it supports query expansion and reformulation by suggesting the exploration of semantically similar concepts, as well as of concepts related to those referred in the query through thematic relations. A test on a data-set collected using the OnToMap Participatory GIS has shown that this approach provides accurate results.
{"title":"Concept-aware geographic information retrieval","authors":"Noemi Mauro, L. Ardissono, Adriano Savoca","doi":"10.1145/3106426.3106498","DOIUrl":"https://doi.org/10.1145/3106426.3106498","url":null,"abstract":"Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, differences in user and system terminologies can challenge the identification of the user's information needs, and thus the generation of relevant results. We argue that the explicit management of ontological knowledge, and of the meaning of concepts (by integrating linguistic and encyclopaedic knowledge in the system ontology), can improve the analysis of search queries, because it enables a flexible identification of the topics the user is searching for, regardless of the adopted vocabulary. This paper proposes an information retrieval support model based on semantic concept identification. Starting from the recognition of the ontology concepts that the search query refers to, this model exploits the qualifiers specified in the query to select information items on the basis of possibly fine-grained features. Moreover, it supports query expansion and reformulation by suggesting the exploration of semantically similar concepts, as well as of concepts related to those referred in the query through thematic relations. A test on a data-set collected using the OnToMap Participatory GIS has shown that this approach provides accurate results.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78438492","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}
Accurate and effective discovery of a brand's key assets, namely, Key Opinion Leaders (KOLs) and potential customers, plays an essential role in marketing campaigns. In a massive online social network, brands are challenged with identifying a small portion of key assets over an enormous volume of irrelevant users, making the problem a highly imbalanced one. Moreover, having to deal with social media data that are usually high-dimensional, the task of brand key asset discovery can be immensely expensive yet inaccurate if the information are not processed efficiently to extract representative features from the original space prior to the learning process. To address the above issues, we propose a novel method dubbed Cluster-wise Biased Discriminant Projection (CBDP) to uncover the compact and informative features from users' data for brand key asset discovery. CBDP conducts a two-layer learning procedure. In the first layer, a Discriminant Clustering (DC) scheme is developed to partition the original dataset into clusters with maximum discriminant capacity. In the second layer, a Biased Discriminant Projection (BDP) algorithm is proposed and performed on each cluster to map the high-dimensional data to the low-dimensional subspace, where the discriminant information of classes with high importance/preference is preserved. A unified mapping function of CBDP is finally established by integrating these two layers. Experiments on both synthetic examples and a real-world brand key asset dataset validate the effectiveness of the proposed method.
{"title":"Brand key asset discovery via cluster-wise biased discriminant projection","authors":"Yang Liu, Zhonglei Gu, Tobey H. Ko, Jiming Liu","doi":"10.1145/3106426.3106516","DOIUrl":"https://doi.org/10.1145/3106426.3106516","url":null,"abstract":"Accurate and effective discovery of a brand's key assets, namely, Key Opinion Leaders (KOLs) and potential customers, plays an essential role in marketing campaigns. In a massive online social network, brands are challenged with identifying a small portion of key assets over an enormous volume of irrelevant users, making the problem a highly imbalanced one. Moreover, having to deal with social media data that are usually high-dimensional, the task of brand key asset discovery can be immensely expensive yet inaccurate if the information are not processed efficiently to extract representative features from the original space prior to the learning process. To address the above issues, we propose a novel method dubbed Cluster-wise Biased Discriminant Projection (CBDP) to uncover the compact and informative features from users' data for brand key asset discovery. CBDP conducts a two-layer learning procedure. In the first layer, a Discriminant Clustering (DC) scheme is developed to partition the original dataset into clusters with maximum discriminant capacity. In the second layer, a Biased Discriminant Projection (BDP) algorithm is proposed and performed on each cluster to map the high-dimensional data to the low-dimensional subspace, where the discriminant information of classes with high importance/preference is preserved. A unified mapping function of CBDP is finally established by integrating these two layers. Experiments on both synthetic examples and a real-world brand key asset dataset validate the effectiveness of the proposed method.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83391067","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}
Contextual enrichment using external sources has been proposed as a means to deal with the poor textual contents of tweets for event classification. Related work performs contextual enrichment according to specific assumptions about the events. Furthermore, enrichment adds a significant amount of extra features, most of them with no discriminative contribution to the event classification task. In this paper, we propose an enrichment framework targeted at the classification of events in general, of which the key elements are: a) external enrichment using related web pages for extending the conceptual features contained within the tweets; b) semantic enrichment using the DBpedia to add related semantic features, and c) a pruning technique that selects the semantic features with discriminative potential. We compared the proposed approach against two distinct baselines based on textual features only and word embeddings, using seven different event datasets. Our experiments reveal that the proposed framework supports the classification of distinct event types, outperforming the textual baseline in 63.5% of the cases, and the word embeddings baseline in 96.5% of the cases.
{"title":"Improving the classification of events in tweets using semantic enrichment","authors":"Simone Aparecida Pinto Romero, Karin Becker","doi":"10.1145/3106426.3106435","DOIUrl":"https://doi.org/10.1145/3106426.3106435","url":null,"abstract":"Contextual enrichment using external sources has been proposed as a means to deal with the poor textual contents of tweets for event classification. Related work performs contextual enrichment according to specific assumptions about the events. Furthermore, enrichment adds a significant amount of extra features, most of them with no discriminative contribution to the event classification task. In this paper, we propose an enrichment framework targeted at the classification of events in general, of which the key elements are: a) external enrichment using related web pages for extending the conceptual features contained within the tweets; b) semantic enrichment using the DBpedia to add related semantic features, and c) a pruning technique that selects the semantic features with discriminative potential. We compared the proposed approach against two distinct baselines based on textual features only and word embeddings, using seven different event datasets. Our experiments reveal that the proposed framework supports the classification of distinct event types, outperforming the textual baseline in 63.5% of the cases, and the word embeddings baseline in 96.5% of the cases.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81887214","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}
This paper exhibits a novel context-aware service framework for IoT based Smart Traffic Management using ontology to regulate smooth traffic flow in smart cities by analyzing real-time traffic environment. The proposed approach makes smarter use of transport networks to achieve objectives related to performance of transport system. This requires efficient traffic planning measures which relate to the actions designed to adjust the demand and capacity of the network in time and space by use of IoT technologies. The adoption of sensors and IoT devices in Smart Traffic System helps to capture the user's preferences and context information which can be in the form of travel time, weather conditions or real-life driving patterns. We have employed multimedia ontology to derive higher level descriptions of traffic conditions and vehicles from perceptual observation of traffic information which provides important grounds for our proposed IoT framework. The multimedia ontology encoded in Multimedia Web Ontology Language(MOWL) helps to define classes, properties, and structure of a possible traffic environment to provide insights across the transportation network. MOWL supports Dynamic Bayesian networks (DBN) to deal with time-series data and uncertainties linked with context observations which fits the definition of an intelligent IoT system. Thus, our proposed smart traffic framework aggregates information corresponding to traffic domain such as traffic videos captured using CCTV cameras and allows automatic prediction of dynamically changing situations which helps to make traffic authorities more responsive. We have illustrated use of our approach by utilizing contextual information, to assess real-time congestion situation on roads thus allowing to visualize planning services. Once the congestion situation is predicted, alternate congestion free routes which are in accordance with the coveted criteria are suggested that can be propagated through text-messages or e-mails to the users.
本文提出了一种新的基于物联网的智能交通管理服务框架,通过分析实时交通环境,利用本体来调节智慧城市的交通顺畅。提出的方法可以更智能地利用运输网络来实现与运输系统性能相关的目标。这需要有效的交通规划措施,这些措施涉及到通过使用物联网技术在时间和空间上调整网络需求和容量的行动。在智能交通系统中采用传感器和物联网设备有助于捕捉用户的偏好和上下文信息,这些信息可以以旅行时间、天气条件或现实驾驶模式的形式呈现。我们使用多媒体本体从对交通信息的感知观察中获得更高层次的交通状况和车辆描述,这为我们提出的物联网框架提供了重要依据。用多媒体Web本体语言(multimedia Web ontology Language, MOWL)编码的多媒体本体有助于定义可能的交通环境的类、属性和结构,从而提供跨交通网络的洞察。MOWL支持动态贝叶斯网络(DBN)来处理时间序列数据和与上下文观测相关的不确定性,符合智能物联网系统的定义。因此,我们提出的智能交通框架聚合了与交通领域相对应的信息,例如使用闭路电视摄像机捕获的交通视频,并允许自动预测动态变化的情况,这有助于交通管理部门做出更快的反应。我们通过使用上下文信息来说明我们的方法的使用,以评估道路上的实时拥堵情况,从而使规划服务可视化。一旦预测到拥堵情况,就会提出符合期望标准的备用无拥堵路线,并通过短信或电子邮件传播给用户。
{"title":"An IoT approach for context-aware smart traffic management using ontology","authors":"Deepti Goel, S. Chaudhury, Hiranmay Ghosh","doi":"10.1145/3106426.3106499","DOIUrl":"https://doi.org/10.1145/3106426.3106499","url":null,"abstract":"This paper exhibits a novel context-aware service framework for IoT based Smart Traffic Management using ontology to regulate smooth traffic flow in smart cities by analyzing real-time traffic environment. The proposed approach makes smarter use of transport networks to achieve objectives related to performance of transport system. This requires efficient traffic planning measures which relate to the actions designed to adjust the demand and capacity of the network in time and space by use of IoT technologies. The adoption of sensors and IoT devices in Smart Traffic System helps to capture the user's preferences and context information which can be in the form of travel time, weather conditions or real-life driving patterns. We have employed multimedia ontology to derive higher level descriptions of traffic conditions and vehicles from perceptual observation of traffic information which provides important grounds for our proposed IoT framework. The multimedia ontology encoded in Multimedia Web Ontology Language(MOWL) helps to define classes, properties, and structure of a possible traffic environment to provide insights across the transportation network. MOWL supports Dynamic Bayesian networks (DBN) to deal with time-series data and uncertainties linked with context observations which fits the definition of an intelligent IoT system. Thus, our proposed smart traffic framework aggregates information corresponding to traffic domain such as traffic videos captured using CCTV cameras and allows automatic prediction of dynamically changing situations which helps to make traffic authorities more responsive. We have illustrated use of our approach by utilizing contextual information, to assess real-time congestion situation on roads thus allowing to visualize planning services. Once the congestion situation is predicted, alternate congestion free routes which are in accordance with the coveted criteria are suggested that can be propagated through text-messages or e-mails to the users.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79565614","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}
Analysis and interpretation of collective feedback on ordinal scales is an important issue for several disciplines, including social sciences, recommender systems research, marketing, political science, and many others. A "reasonable" model is expected to provide an "explanation" of collective user behaviour. Many existing data mining approaches employ for this purpose probabilistic models, based on distributions and mixtures from a certain parametric family. In real life, users meet their decisions with considerable uncertainty. Its assessment and use in probabilistic models for better interpretation of collective feedback is the key concern of this paper. In doing so, we introduce approaches for gathering individual uncertainty, and discuss their viability and limitations. Consequently, we enrich state of the art response mining models (especially focused on discovery of latent user groups) with uncertainty knowledge, and demonstrate resulting advantages in systematic experiments with real users.
{"title":"Mining ordinal data under human response uncertainty","authors":"Sergej Sizov","doi":"10.1145/3106426.3106448","DOIUrl":"https://doi.org/10.1145/3106426.3106448","url":null,"abstract":"Analysis and interpretation of collective feedback on ordinal scales is an important issue for several disciplines, including social sciences, recommender systems research, marketing, political science, and many others. A \"reasonable\" model is expected to provide an \"explanation\" of collective user behaviour. Many existing data mining approaches employ for this purpose probabilistic models, based on distributions and mixtures from a certain parametric family. In real life, users meet their decisions with considerable uncertainty. Its assessment and use in probabilistic models for better interpretation of collective feedback is the key concern of this paper. In doing so, we introduce approaches for gathering individual uncertainty, and discuss their viability and limitations. Consequently, we enrich state of the art response mining models (especially focused on discovery of latent user groups) with uncertainty knowledge, and demonstrate resulting advantages in systematic experiments with real users.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72876883","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}
Wenbo Wang, Lu Chen, Keke Chen, K. Thirunarayan, A. Sheth
This paper exploits a large number of self-labeled emotion tweets as the training data from the source domain to improve emotion identification in target domains (i.e., blogs and fairy tales), where there is a short supply of labeled data. Due to the noisy and ambiguous nature of self-labeled emotion training data, the existing domain adaptation methods that typically depend on high-quality labeled source-domain data do not work satisfactorily. This paper describes an adaptive source-domain training instance selection method to address the problem of noisy source-domain training data. The proposed approach can effectively identify the most informative training examples based on three carefully designed measures: consistency, diversity, and similarity. It uses an iterative method that consists of the following steps in each iteration: selecting informative samples from the source domain with the informativeness measures, merging with the target-domain training data, evaluating the performance of learned classifier for the target domain, and updating the informativeness measures for the next iteration. It stops until no new training instance is selected or in a designated number of iterations. Experiments show that our approach performs effectively for cross-domain emotion identification and consistently outperforms baseline approaches across four domains.
{"title":"Adaptive training instance selection for cross-domain emotion identification","authors":"Wenbo Wang, Lu Chen, Keke Chen, K. Thirunarayan, A. Sheth","doi":"10.1145/3106426.3106457","DOIUrl":"https://doi.org/10.1145/3106426.3106457","url":null,"abstract":"This paper exploits a large number of self-labeled emotion tweets as the training data from the source domain to improve emotion identification in target domains (i.e., blogs and fairy tales), where there is a short supply of labeled data. Due to the noisy and ambiguous nature of self-labeled emotion training data, the existing domain adaptation methods that typically depend on high-quality labeled source-domain data do not work satisfactorily. This paper describes an adaptive source-domain training instance selection method to address the problem of noisy source-domain training data. The proposed approach can effectively identify the most informative training examples based on three carefully designed measures: consistency, diversity, and similarity. It uses an iterative method that consists of the following steps in each iteration: selecting informative samples from the source domain with the informativeness measures, merging with the target-domain training data, evaluating the performance of learned classifier for the target domain, and updating the informativeness measures for the next iteration. It stops until no new training instance is selected or in a designated number of iterations. Experiments show that our approach performs effectively for cross-domain emotion identification and consistently outperforms baseline approaches across four domains.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77050350","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}
Falak Nawaz, O. Hussain, N. Janjua, Elizabeth Chang
Cloud-of-things service providers use various descriptions languages to describe Quality of Service (QoS) attributes. However, existing modelling approaches provide support for modelling static QoS attributes only and lack features to model and reason with dynamic QoS attributes such as response time and availability. This paper presents an event-based approach for monitoring dynamic QoS values and their compliance by modelling the behavior of QoS attributes using an Event Calculus (EC) based framework. The logic based reasoning is then performed to proactively identify the possible QoS violations in future.
{"title":"A proactive event-driven approach for dynamic QoS compliance in cloud of things","authors":"Falak Nawaz, O. Hussain, N. Janjua, Elizabeth Chang","doi":"10.1145/3106426.3109431","DOIUrl":"https://doi.org/10.1145/3106426.3109431","url":null,"abstract":"Cloud-of-things service providers use various descriptions languages to describe Quality of Service (QoS) attributes. However, existing modelling approaches provide support for modelling static QoS attributes only and lack features to model and reason with dynamic QoS attributes such as response time and availability. This paper presents an event-based approach for monitoring dynamic QoS values and their compliance by modelling the behavior of QoS attributes using an Event Calculus (EC) based framework. The logic based reasoning is then performed to proactively identify the possible QoS violations in future.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78228955","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}
To improve the effectiveness of users' information seeking experience in interactive web search we hypothesize how people might be influenced when making relevance judgment decisions by introducing the Consensus Theory & Relevance Judgment Model (CT&M). This is combined with a practical path to assess the extent of difference between suggestions of current search engines versus user expectations. A user-centered, evidence-based, phenomenology approach is used to improve on Google PageRank (GPR) in two ways. The first by biasing GPR's equal navigation probability assumption using (f)actual usage stats as implicit user consensus which leads to the StatsRank (SR) algorithm. Secondly, we aggregate users' explicit ranking to derive Consensus Rank (CR) which is shown to predict individual user ranking significantly better than GPR and meta-search of modern search engines Google and Yahoo/Bing real-time. CT&M contextualizes CR, SR, and a live open online web experiment, called The Ranking Game, which is based on the August-2016 English Wikipedia corpus (12.7 million pages) and Page View Statistics for May to July 2016. Limiting this work to Wikipedia makes GPR topic-based since any Wikipedia page is focused on one topic. TREC's pooling is used to merge top 20 results from major search engines and present an alphabetized list for users' explicit ranking via drag and drop. The same platform captures implicit data for future research and can be used for controlled experiments. Our contributions are: CT&M, SR, CR, and the open online user feedback web experiment research platform.
{"title":"Consensus-based ranking of wikipedia topics","authors":"Waleed Nema, Yinshan Tang","doi":"10.1145/3106426.3106529","DOIUrl":"https://doi.org/10.1145/3106426.3106529","url":null,"abstract":"To improve the effectiveness of users' information seeking experience in interactive web search we hypothesize how people might be influenced when making relevance judgment decisions by introducing the Consensus Theory & Relevance Judgment Model (CT&M). This is combined with a practical path to assess the extent of difference between suggestions of current search engines versus user expectations. A user-centered, evidence-based, phenomenology approach is used to improve on Google PageRank (GPR) in two ways. The first by biasing GPR's equal navigation probability assumption using (f)actual usage stats as implicit user consensus which leads to the StatsRank (SR) algorithm. Secondly, we aggregate users' explicit ranking to derive Consensus Rank (CR) which is shown to predict individual user ranking significantly better than GPR and meta-search of modern search engines Google and Yahoo/Bing real-time. CT&M contextualizes CR, SR, and a live open online web experiment, called The Ranking Game, which is based on the August-2016 English Wikipedia corpus (12.7 million pages) and Page View Statistics for May to July 2016. Limiting this work to Wikipedia makes GPR topic-based since any Wikipedia page is focused on one topic. TREC's pooling is used to merge top 20 results from major search engines and present an alphabetized list for users' explicit ranking via drag and drop. The same platform captures implicit data for future research and can be used for controlled experiments. Our contributions are: CT&M, SR, CR, and the open online user feedback web experiment research platform.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75260427","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}
N. Janjua, O. Hussain, Elizabeth Chang, S. M. Islam
Effective business planning requires seamless access and intelligent analysis of information in its totality to allow the business planner to gain enhanced critical business insights for decision support. Current business planning tools provide insights from structured business data (i.e. sales forecasts, customers and products data, inventory details) only and fail to take into account unstructured complementary information residing in contracts, reports, user's comments, emails etc. In this article, a planning support system is designed and developed that empower business planners to develop and revise business plans utilizing both structured data and unstructured information conjointly. This planning system activity model comprises of two steps. Firstly, a business planner develops a candidate plan using planning template. Secondly, the candidate plan is put forward to collaborating partners for its revision interleaving deliberation. Planning interleaving deliberation activity in the proposed framework enables collaborating planners to challenge both a decision and the thinking that underpins the decision in the candidate plan. The planning system is modeled using situation calculus and is validated through a prototype development.
{"title":"Conjoint utilization of structured and unstructured information for planning interleaving deliberation in supply chains","authors":"N. Janjua, O. Hussain, Elizabeth Chang, S. M. Islam","doi":"10.1145/3106426.3106545","DOIUrl":"https://doi.org/10.1145/3106426.3106545","url":null,"abstract":"Effective business planning requires seamless access and intelligent analysis of information in its totality to allow the business planner to gain enhanced critical business insights for decision support. Current business planning tools provide insights from structured business data (i.e. sales forecasts, customers and products data, inventory details) only and fail to take into account unstructured complementary information residing in contracts, reports, user's comments, emails etc. In this article, a planning support system is designed and developed that empower business planners to develop and revise business plans utilizing both structured data and unstructured information conjointly. This planning system activity model comprises of two steps. Firstly, a business planner develops a candidate plan using planning template. Secondly, the candidate plan is put forward to collaborating partners for its revision interleaving deliberation. Planning interleaving deliberation activity in the proposed framework enables collaborating planners to challenge both a decision and the thinking that underpins the decision in the candidate plan. The planning system is modeled using situation calculus and is validated through a prototype development.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75556976","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}
This paper analyzes the lexical semantics of domain-specific terms based on various pre-trained specific domain and general domain word vectors, and addresses the semantic drift between domains. To capture lexical semantics in the specific domain, we propose a bridge mechanism to introduce domain-specific data into general data, and re-train word vectors. We find that even a small-scale fusion can result in the similar lexical semantics learned by using the large-scale domain-specific dataset. Experiments on sentiment analysis and outlier detection show that application of word embedding by the fusion dataset has the better performance than applications of word embeddings by pure large domain-specific and pure large general datasets. The simple, but effective methodology facilitates the domain adaptation of distributed word representations.
{"title":"Fusing domain-specific data with general data for in-domain applications","authors":"An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen","doi":"10.1145/3106426.3106473","DOIUrl":"https://doi.org/10.1145/3106426.3106473","url":null,"abstract":"This paper analyzes the lexical semantics of domain-specific terms based on various pre-trained specific domain and general domain word vectors, and addresses the semantic drift between domains. To capture lexical semantics in the specific domain, we propose a bridge mechanism to introduce domain-specific data into general data, and re-train word vectors. We find that even a small-scale fusion can result in the similar lexical semantics learned by using the large-scale domain-specific dataset. Experiments on sentiment analysis and outlier detection show that application of word embedding by the fusion dataset has the better performance than applications of word embeddings by pure large domain-specific and pure large general datasets. The simple, but effective methodology facilitates the domain adaptation of distributed word representations.","PeriodicalId":20685,"journal":{"name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77505154","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}