Rubrics provides standardization in evaluation by specifying guidelines to assign marks according... more Rubrics provides standardization in evaluation by specifying guidelines to assign marks according to predetermined evaluation criteria. Rubrics-based evaluation for final year project in computer science has typically focused on the proposal writing, seminar, prototype development, logbook maintenance and dissertation writing. However, the evaluation has often overlooked the innovativeness of the project nor entrepreneurship skills of the candidates. This paper addresses the gap of current implementation of final year project implementation and introduce a framework of innovation-enhanced rubrics-based evaluation for final year project. The new assessment framework emphasizes the entrepreneurship and innovation skills which are realized cognitive, affective, psychomotor, soft skill as well as life-long learning characteristics in the course implementation. The new framework has resulted to candidates who have acquired a more holistics attributes of excellent fresh graduates which are important and highly looked by the employers.
The big data phenomenon has confirmed the achievement of data access transformation. Sentiment an... more The big data phenomenon has confirmed the achievement of data access transformation. Sentiment analysis (SA) is one of the most exploited area and used for profit-making purpose through business intelligence applications. This paper reviews the trends in SA and relates the growth in the area with the big data era
The semantic technology enhances big data advancements by allowing sophisticated analysis of text... more The semantic technology enhances big data advancements by allowing sophisticated analysis of texts. Through the Linked Data technology, tremendous amount of information can be connected. However, this inherits ambiguity when it needs to be manipulated for certain purpose like natural language interface, semantic search and question answering. There are limited works which address ambiguity in semantic search. This paper introduces a technique based on self-adaptive disambiguation which utilizes the possible concept annotations of terms in the natural language queries. This will allow users to compose query in natural language and receive accurate answers without having to master the formal syntax of the semantic query language.
Proceedings of International Conference on Intelligent Systems Design and Applications
Umrah as a pilgrimage to Mecca is obligatory in Islam
madhab. Pilgrims can gain their knowledge ... more Umrah as a pilgrimage to Mecca is obligatory in Islam
madhab. Pilgrims can gain their knowledge about the
requirements of Umrah using books, expert and existent question
answering systems but still they suffer from the lack of
complexity and natural language patterns. This paper proposes
the semantic based question answering system to able pilgrims to
compose any question about Umrah in natural language format.
The proposed system used ontology to represent the knowledge
about ritual of Umrah and Pilgrims. The question complexity for
question in natural language is observed since it needs to be map
with the contents in the ontology. An Umrah Knowledge module
in this system covers all the rules and fact in the ontology format
and the Educational modules is responsible for question
answering interaction.
Proceedings of the International Conference of Intelligent Systems Design and Applications, 2013
Since the emergence of ontologies in the field of
computer science a number of approaches for de... more Since the emergence of ontologies in the field of
computer science a number of approaches for developing
ontologies have been proposed. Different approaches focus on
distinct aspects of the ontology development process and make
use of various techniques for developing ontologies. It is an
accepted fact that the ontology development process relies on
human feedback and decisions during various phases of
ontology development. However, most of the existing
approaches neglect this aspect of ontology development. In
order to bridge this gap, this paper proposes an ontology
development approach using the concept mapping technique,
which is human centered in nature. This approach eases the
overall ontology development process. It allows developing
ontologies which involve human feedback during the evolution
of the ontology design.
Proceedings of International Conference on Intelligent Systems Design and Applications, 2013
Deceptive opinion classification has attracted a lot
of research interest due to the rapid growth... more Deceptive opinion classification has attracted a lot
of research interest due to the rapid growth of social media
users. Despite the availability of a vast number of opinion
features and classification techniques, review classification still
remains a challenging task. In this work we applied stylometric
features, i.e. lexical and syntactic, using supervised machine
learning classifiers, i.e. Support Vector Machine (SVM) with
Sequential Minimal Optimization (SMO) and Naive Bayes,
to detect deceptive opinion. Detecting deceptive opinion by
a human reader is a difficult task because spammers try to
write wise reviews, therefore it causes changes in writing style
and verbal usage. Hence, considering the stylometric features
help to distinguish the spammer writing style to find deceptive
reviews. Experiments on an existing hotel review corpus suggest
that using stylometric features is a promising approach for
detecting deceptive opinions.
Proceedings of the International Conference of Internet and Society 2013 (ITS2013), 2013
Technology has influenced the need of having recommendation systems in many areas of daily life. ... more Technology has influenced the need of having recommendation systems in many areas of daily life. The main feature of
the recommendation system is the personalization which tailored information according to users’ needs and adaptation
which responds to users’ needs in a suitable manner as their preferences change. Numerous techniques like contentbased,
collaborative, demographic and semantic recommendation have already been proposed. Sometimes the
combination of these techniques called the hybrid recommendation is used for better results. Different strategies are used
to combine recommendation techniques in the hybrid recommendation method such as weighted, cascading and feature
augmented hybrid. This paper presents mobile software called Travel-Buddy, which will focus on personalized
recommendation in tourism domain. The system combines the content-based, collaborative, demographic and semantic
techniques in and implemented in a weighted and cascading recommendation formulation. Our preliminary work shows
that this hybrid approach can mitigate the weaknesses shown by these recommendation techniques when used
individually.
KEYWORDS
Proceedings of the Internet Technology and Society 2013 (ITS2013), 2013
A number of ontology engineering methodologies have been proposed to date. Distinct methodologies... more A number of ontology engineering methodologies have been proposed to date. Distinct methodologies rely on different
techniques and activities to carry out the development of an ontology. The concept mapping technique has been recently
used for developing ontologies related to different domains. However, the existing approaches using concept mapping do
not make use of any automatic term extraction process to ease the overall ontology development process. This paper
proposes a new approach which uses the concept mapping technique coupled with a Term Extraction Engine (TEE). The
engine automatically extracts the candidate terms from the competency questions which are later used for creating the
concept map. This concept map is later transformed in to a working ontology. The proposed approach reduces human
efforts and eases the ontology development process.
Querying semantic knowledge base often requires the understanding of the ontology schema and pro... more Querying semantic knowledge base often requires the understanding of the ontology schema and proficiency with the query language. Several approaches have existed but mainly dealing with the disambiguation problem which are solved by executing clarification dialogues. This paper addresses the automatic translation of natural language queries into its SPARQL equivalent statement without involving clarification dialogues. We demonstrate that this is achieveable by by annotating all ontology concepts in the query. Next the connections between the classes are identified so that the shared properties can be loaded before they are matched with the terms in the query. Then, the identified ontology triples are arranged to construct a valid SPARQL query according to their relation in the ontology schema. We compare the performance of MyAutoSPARQL against FREyA, an NLI that utilizes clarification dialogue. We evaluate our approach on selection typed queries and compare the performance against FREyA. The results show that despite the absent of clarification dialogues, MyAutoSPARQL performance is better than FREyA.
"Semantic question answering demand different processing compared to the common information retri... more "Semantic question answering demand different processing compared to the common information retrieval based question answering method because the semantic knowledge base is stored in the triples form. However, manipulating the knowledge requires understanding its structure and proficiency in semantic query language such as SPARQL. Natural language interface alleviates this by allowing user to input question in their human language and produce an answer by translating the input into an equivalent SPARQL before it is executed to retrieve the answer. However, several challenges exist such as concept identification,
compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question
complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned. "
It is now widely accepted that ontologies play a critical role in achieving the goal of machine
... more It is now widely accepted that ontologies play a critical role in achieving the goal of machine
understandable web, also known as semantic web. In order to develop ontologies, several methodologies have been
proposed during the last two decades. Despite the fact, that quite a number of ontology engineering methodologies
have been proposed, still the field lacks widely accepted and mature methodologies. Most methodologies lack
sufficient details of techniques and activities employed in them. However, some methodologies provide sufficient
details including METHONTOLOGY. This article discusses and reports a critical analysis and comparison of these
methodologies. The analysis is performed based on a criterion, derived from related literature, trends and needs
which evolved over the years. The results of the analysis showed that there is no completely mature methodology.
Therefore, this research may act as a preliminary guide to come with a state of art ontology engineering
methodology, bridging up the existing gaps and shortfalls.
Proceedings of the 4th International Conference on Computing and Informatics, ICOCI 2013, Aug 28, 2013
Semantic question answering is a discipline that allows the development of smart systems through ... more Semantic question answering is a discipline that allows the development of smart systems through its reasoning and natural language understanding capability. Knowledge is stored based on representation format such as ontology. However, querying these knowledge requires understanding of the knowledge structure and demands the user to be equipped with the formal query construction skill. This will definitely hinder the development of this area. Therefore this paper addresses the translation model of constraints-typed questions. We focus on the components that relate to constraints-typed question answering and propose a computational model for the translation. These figures indicate promising development in this problem and should encourage more alternative methods in the same direction.
Automatic lexicon generation is a useful task in learning text fragment patterns. In our previous... more Automatic lexicon generation is a useful task in learning text fragment patterns. In our previous
work we have focused on text fragment pattern learning through the fuzzy grammar method which
inputs include a predefined lexicon and text fragments that represents the expression of the grammar
class to be learned. However, the bottleneck of the success of the fuzzy grammar creation and in
common with other text learner often lies in the knowledge acquisition phase; due to the labour
intensive text annotation which also demands skills and background knowledge of the text. For this
reason, a semi-automated technique called automatic Terminal Grammar Recommender (TGR) is
devised to identify conceptually related lexicons in the texts and their related to create terminal
grammars by mining associations of words contexts. The approach recognizes that there is a degree of
local structure within such text and the technique exploits the local structure without the large
computational overhead of deeper analysis. Result from the comparison of the associative words
detected by TGR with the definition of a content category tool called General Inquirer on the data from
European Central Bank data is reported. Our findings show that our proposed method has managed to
reduce the manual effort of identifying conceptually similar lexicons to form terminal grammars. The
average of matched generated terminal grammar clusters compared to General Inquirer is 54.85%
which indicates that at least half the expensive effort to construct conceptually related lexicon is saved.
This hint the potential of word context association mining in automated conceptual lexicon generation.
Natural language interface (NLI) allows user to communicate with the semantic knowledge base thro... more Natural language interface (NLI) allows user to communicate with the semantic knowledge base through natural language (NL). However, several challenges exist such as understanding user’s intention in the query and matching the elements in the query with the knowledge base (KB). Several solutions exist but were developed differently in terms of query processing components, query matching style and expressivity support. The focus of the autoSPARQL application introduced in this paper is the soft queries processing and the result is compared against FREyA, an NLI equipped with clarification dialogue component. Result has demonstrated that there is no significant difference between these applications. The results also open rooms for future works such as re-testing in bigger scale and more concrete numerical and semantic expression processing.
International Conference on Information Retrieval & Knowledge Management (CAMP) 2012 , Mar 2012
Medical information retrieval demands terminology understanding which indicates the needs for dom... more Medical information retrieval demands terminology understanding which indicates the needs for domain specific knowledge. This paper presents a medical retrieval model called IntelligentMedicalSearch system (IMS). The contribution of the paper is four-fold: (i) medical-aware query expansion technique; (ii) MeSH-manipulated indexer which entails medical terminologies and their synonym (iii) extended Boolean matching to measure similarity between query and documents; (iv) comprehensive ranking method which prioritizes matched expanded query size besides sole total occurrence score. Result shown that (i) enrichment of query expansion using synonym term can improve mean average precision (MAP) value as opposed to standard query expansion; (iii) our comprehensive ranking method achieved high recall and according to MAP score we are in the top four run system amongst submitted run systems in ImageCLEF2010 medical task.
Text mining saves the necessity to sift through vast amount of documents manually to find relevan... more Text mining saves the necessity to sift through vast amount of documents manually to find relevant information. This paper focuses on text categorization, one of the tasks under text mining. This paper introduces fuzzy grammar as a technique for building text classifier and investigates the performance of fuzzy grammar against other machine learning methods such as decision table, support vector machine, statistic, nearest neighbor and boosting. Incidents dataset was used where the focus was given on classifying the incidents events. Results have shown that fuzzy grammar has gotten promising results among the other benchmark machine learning methods.
Fuzzy grammar has been introduced as an approach to represent and learn text fragments where the ... more Fuzzy grammar has been introduced as an approach to represent and learn text fragments where the set of learned patterns are represented by combining similar segments to represent regularities and marking interchangeable segments. This paper is dedicated to present a procedural scheme towards learning text fragment in text categorization task facilitated by fuzzy grammars.
Rubrics provides standardization in evaluation by specifying guidelines to assign marks according... more Rubrics provides standardization in evaluation by specifying guidelines to assign marks according to predetermined evaluation criteria. Rubrics-based evaluation for final year project in computer science has typically focused on the proposal writing, seminar, prototype development, logbook maintenance and dissertation writing. However, the evaluation has often overlooked the innovativeness of the project nor entrepreneurship skills of the candidates. This paper addresses the gap of current implementation of final year project implementation and introduce a framework of innovation-enhanced rubrics-based evaluation for final year project. The new assessment framework emphasizes the entrepreneurship and innovation skills which are realized cognitive, affective, psychomotor, soft skill as well as life-long learning characteristics in the course implementation. The new framework has resulted to candidates who have acquired a more holistics attributes of excellent fresh graduates which are important and highly looked by the employers.
The big data phenomenon has confirmed the achievement of data access transformation. Sentiment an... more The big data phenomenon has confirmed the achievement of data access transformation. Sentiment analysis (SA) is one of the most exploited area and used for profit-making purpose through business intelligence applications. This paper reviews the trends in SA and relates the growth in the area with the big data era
The semantic technology enhances big data advancements by allowing sophisticated analysis of text... more The semantic technology enhances big data advancements by allowing sophisticated analysis of texts. Through the Linked Data technology, tremendous amount of information can be connected. However, this inherits ambiguity when it needs to be manipulated for certain purpose like natural language interface, semantic search and question answering. There are limited works which address ambiguity in semantic search. This paper introduces a technique based on self-adaptive disambiguation which utilizes the possible concept annotations of terms in the natural language queries. This will allow users to compose query in natural language and receive accurate answers without having to master the formal syntax of the semantic query language.
Proceedings of International Conference on Intelligent Systems Design and Applications
Umrah as a pilgrimage to Mecca is obligatory in Islam
madhab. Pilgrims can gain their knowledge ... more Umrah as a pilgrimage to Mecca is obligatory in Islam
madhab. Pilgrims can gain their knowledge about the
requirements of Umrah using books, expert and existent question
answering systems but still they suffer from the lack of
complexity and natural language patterns. This paper proposes
the semantic based question answering system to able pilgrims to
compose any question about Umrah in natural language format.
The proposed system used ontology to represent the knowledge
about ritual of Umrah and Pilgrims. The question complexity for
question in natural language is observed since it needs to be map
with the contents in the ontology. An Umrah Knowledge module
in this system covers all the rules and fact in the ontology format
and the Educational modules is responsible for question
answering interaction.
Proceedings of the International Conference of Intelligent Systems Design and Applications, 2013
Since the emergence of ontologies in the field of
computer science a number of approaches for de... more Since the emergence of ontologies in the field of
computer science a number of approaches for developing
ontologies have been proposed. Different approaches focus on
distinct aspects of the ontology development process and make
use of various techniques for developing ontologies. It is an
accepted fact that the ontology development process relies on
human feedback and decisions during various phases of
ontology development. However, most of the existing
approaches neglect this aspect of ontology development. In
order to bridge this gap, this paper proposes an ontology
development approach using the concept mapping technique,
which is human centered in nature. This approach eases the
overall ontology development process. It allows developing
ontologies which involve human feedback during the evolution
of the ontology design.
Proceedings of International Conference on Intelligent Systems Design and Applications, 2013
Deceptive opinion classification has attracted a lot
of research interest due to the rapid growth... more Deceptive opinion classification has attracted a lot
of research interest due to the rapid growth of social media
users. Despite the availability of a vast number of opinion
features and classification techniques, review classification still
remains a challenging task. In this work we applied stylometric
features, i.e. lexical and syntactic, using supervised machine
learning classifiers, i.e. Support Vector Machine (SVM) with
Sequential Minimal Optimization (SMO) and Naive Bayes,
to detect deceptive opinion. Detecting deceptive opinion by
a human reader is a difficult task because spammers try to
write wise reviews, therefore it causes changes in writing style
and verbal usage. Hence, considering the stylometric features
help to distinguish the spammer writing style to find deceptive
reviews. Experiments on an existing hotel review corpus suggest
that using stylometric features is a promising approach for
detecting deceptive opinions.
Proceedings of the International Conference of Internet and Society 2013 (ITS2013), 2013
Technology has influenced the need of having recommendation systems in many areas of daily life. ... more Technology has influenced the need of having recommendation systems in many areas of daily life. The main feature of
the recommendation system is the personalization which tailored information according to users’ needs and adaptation
which responds to users’ needs in a suitable manner as their preferences change. Numerous techniques like contentbased,
collaborative, demographic and semantic recommendation have already been proposed. Sometimes the
combination of these techniques called the hybrid recommendation is used for better results. Different strategies are used
to combine recommendation techniques in the hybrid recommendation method such as weighted, cascading and feature
augmented hybrid. This paper presents mobile software called Travel-Buddy, which will focus on personalized
recommendation in tourism domain. The system combines the content-based, collaborative, demographic and semantic
techniques in and implemented in a weighted and cascading recommendation formulation. Our preliminary work shows
that this hybrid approach can mitigate the weaknesses shown by these recommendation techniques when used
individually.
KEYWORDS
Proceedings of the Internet Technology and Society 2013 (ITS2013), 2013
A number of ontology engineering methodologies have been proposed to date. Distinct methodologies... more A number of ontology engineering methodologies have been proposed to date. Distinct methodologies rely on different
techniques and activities to carry out the development of an ontology. The concept mapping technique has been recently
used for developing ontologies related to different domains. However, the existing approaches using concept mapping do
not make use of any automatic term extraction process to ease the overall ontology development process. This paper
proposes a new approach which uses the concept mapping technique coupled with a Term Extraction Engine (TEE). The
engine automatically extracts the candidate terms from the competency questions which are later used for creating the
concept map. This concept map is later transformed in to a working ontology. The proposed approach reduces human
efforts and eases the ontology development process.
Querying semantic knowledge base often requires the understanding of the ontology schema and pro... more Querying semantic knowledge base often requires the understanding of the ontology schema and proficiency with the query language. Several approaches have existed but mainly dealing with the disambiguation problem which are solved by executing clarification dialogues. This paper addresses the automatic translation of natural language queries into its SPARQL equivalent statement without involving clarification dialogues. We demonstrate that this is achieveable by by annotating all ontology concepts in the query. Next the connections between the classes are identified so that the shared properties can be loaded before they are matched with the terms in the query. Then, the identified ontology triples are arranged to construct a valid SPARQL query according to their relation in the ontology schema. We compare the performance of MyAutoSPARQL against FREyA, an NLI that utilizes clarification dialogue. We evaluate our approach on selection typed queries and compare the performance against FREyA. The results show that despite the absent of clarification dialogues, MyAutoSPARQL performance is better than FREyA.
"Semantic question answering demand different processing compared to the common information retri... more "Semantic question answering demand different processing compared to the common information retrieval based question answering method because the semantic knowledge base is stored in the triples form. However, manipulating the knowledge requires understanding its structure and proficiency in semantic query language such as SPARQL. Natural language interface alleviates this by allowing user to input question in their human language and produce an answer by translating the input into an equivalent SPARQL before it is executed to retrieve the answer. However, several challenges exist such as concept identification,
compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question
complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned. "
It is now widely accepted that ontologies play a critical role in achieving the goal of machine
... more It is now widely accepted that ontologies play a critical role in achieving the goal of machine
understandable web, also known as semantic web. In order to develop ontologies, several methodologies have been
proposed during the last two decades. Despite the fact, that quite a number of ontology engineering methodologies
have been proposed, still the field lacks widely accepted and mature methodologies. Most methodologies lack
sufficient details of techniques and activities employed in them. However, some methodologies provide sufficient
details including METHONTOLOGY. This article discusses and reports a critical analysis and comparison of these
methodologies. The analysis is performed based on a criterion, derived from related literature, trends and needs
which evolved over the years. The results of the analysis showed that there is no completely mature methodology.
Therefore, this research may act as a preliminary guide to come with a state of art ontology engineering
methodology, bridging up the existing gaps and shortfalls.
Proceedings of the 4th International Conference on Computing and Informatics, ICOCI 2013, Aug 28, 2013
Semantic question answering is a discipline that allows the development of smart systems through ... more Semantic question answering is a discipline that allows the development of smart systems through its reasoning and natural language understanding capability. Knowledge is stored based on representation format such as ontology. However, querying these knowledge requires understanding of the knowledge structure and demands the user to be equipped with the formal query construction skill. This will definitely hinder the development of this area. Therefore this paper addresses the translation model of constraints-typed questions. We focus on the components that relate to constraints-typed question answering and propose a computational model for the translation. These figures indicate promising development in this problem and should encourage more alternative methods in the same direction.
Automatic lexicon generation is a useful task in learning text fragment patterns. In our previous... more Automatic lexicon generation is a useful task in learning text fragment patterns. In our previous
work we have focused on text fragment pattern learning through the fuzzy grammar method which
inputs include a predefined lexicon and text fragments that represents the expression of the grammar
class to be learned. However, the bottleneck of the success of the fuzzy grammar creation and in
common with other text learner often lies in the knowledge acquisition phase; due to the labour
intensive text annotation which also demands skills and background knowledge of the text. For this
reason, a semi-automated technique called automatic Terminal Grammar Recommender (TGR) is
devised to identify conceptually related lexicons in the texts and their related to create terminal
grammars by mining associations of words contexts. The approach recognizes that there is a degree of
local structure within such text and the technique exploits the local structure without the large
computational overhead of deeper analysis. Result from the comparison of the associative words
detected by TGR with the definition of a content category tool called General Inquirer on the data from
European Central Bank data is reported. Our findings show that our proposed method has managed to
reduce the manual effort of identifying conceptually similar lexicons to form terminal grammars. The
average of matched generated terminal grammar clusters compared to General Inquirer is 54.85%
which indicates that at least half the expensive effort to construct conceptually related lexicon is saved.
This hint the potential of word context association mining in automated conceptual lexicon generation.
Natural language interface (NLI) allows user to communicate with the semantic knowledge base thro... more Natural language interface (NLI) allows user to communicate with the semantic knowledge base through natural language (NL). However, several challenges exist such as understanding user’s intention in the query and matching the elements in the query with the knowledge base (KB). Several solutions exist but were developed differently in terms of query processing components, query matching style and expressivity support. The focus of the autoSPARQL application introduced in this paper is the soft queries processing and the result is compared against FREyA, an NLI equipped with clarification dialogue component. Result has demonstrated that there is no significant difference between these applications. The results also open rooms for future works such as re-testing in bigger scale and more concrete numerical and semantic expression processing.
International Conference on Information Retrieval & Knowledge Management (CAMP) 2012 , Mar 2012
Medical information retrieval demands terminology understanding which indicates the needs for dom... more Medical information retrieval demands terminology understanding which indicates the needs for domain specific knowledge. This paper presents a medical retrieval model called IntelligentMedicalSearch system (IMS). The contribution of the paper is four-fold: (i) medical-aware query expansion technique; (ii) MeSH-manipulated indexer which entails medical terminologies and their synonym (iii) extended Boolean matching to measure similarity between query and documents; (iv) comprehensive ranking method which prioritizes matched expanded query size besides sole total occurrence score. Result shown that (i) enrichment of query expansion using synonym term can improve mean average precision (MAP) value as opposed to standard query expansion; (iii) our comprehensive ranking method achieved high recall and according to MAP score we are in the top four run system amongst submitted run systems in ImageCLEF2010 medical task.
Text mining saves the necessity to sift through vast amount of documents manually to find relevan... more Text mining saves the necessity to sift through vast amount of documents manually to find relevant information. This paper focuses on text categorization, one of the tasks under text mining. This paper introduces fuzzy grammar as a technique for building text classifier and investigates the performance of fuzzy grammar against other machine learning methods such as decision table, support vector machine, statistic, nearest neighbor and boosting. Incidents dataset was used where the focus was given on classifying the incidents events. Results have shown that fuzzy grammar has gotten promising results among the other benchmark machine learning methods.
Fuzzy grammar has been introduced as an approach to represent and learn text fragments where the ... more Fuzzy grammar has been introduced as an approach to represent and learn text fragments where the set of learned patterns are represented by combining similar segments to represent regularities and marking interchangeable segments. This paper is dedicated to present a procedural scheme towards learning text fragment in text categorization task facilitated by fuzzy grammars.
Uploads
madhab. Pilgrims can gain their knowledge about the
requirements of Umrah using books, expert and existent question
answering systems but still they suffer from the lack of
complexity and natural language patterns. This paper proposes
the semantic based question answering system to able pilgrims to
compose any question about Umrah in natural language format.
The proposed system used ontology to represent the knowledge
about ritual of Umrah and Pilgrims. The question complexity for
question in natural language is observed since it needs to be map
with the contents in the ontology. An Umrah Knowledge module
in this system covers all the rules and fact in the ontology format
and the Educational modules is responsible for question
answering interaction.
computer science a number of approaches for developing
ontologies have been proposed. Different approaches focus on
distinct aspects of the ontology development process and make
use of various techniques for developing ontologies. It is an
accepted fact that the ontology development process relies on
human feedback and decisions during various phases of
ontology development. However, most of the existing
approaches neglect this aspect of ontology development. In
order to bridge this gap, this paper proposes an ontology
development approach using the concept mapping technique,
which is human centered in nature. This approach eases the
overall ontology development process. It allows developing
ontologies which involve human feedback during the evolution
of the ontology design.
of research interest due to the rapid growth of social media
users. Despite the availability of a vast number of opinion
features and classification techniques, review classification still
remains a challenging task. In this work we applied stylometric
features, i.e. lexical and syntactic, using supervised machine
learning classifiers, i.e. Support Vector Machine (SVM) with
Sequential Minimal Optimization (SMO) and Naive Bayes,
to detect deceptive opinion. Detecting deceptive opinion by
a human reader is a difficult task because spammers try to
write wise reviews, therefore it causes changes in writing style
and verbal usage. Hence, considering the stylometric features
help to distinguish the spammer writing style to find deceptive
reviews. Experiments on an existing hotel review corpus suggest
that using stylometric features is a promising approach for
detecting deceptive opinions.
the recommendation system is the personalization which tailored information according to users’ needs and adaptation
which responds to users’ needs in a suitable manner as their preferences change. Numerous techniques like contentbased,
collaborative, demographic and semantic recommendation have already been proposed. Sometimes the
combination of these techniques called the hybrid recommendation is used for better results. Different strategies are used
to combine recommendation techniques in the hybrid recommendation method such as weighted, cascading and feature
augmented hybrid. This paper presents mobile software called Travel-Buddy, which will focus on personalized
recommendation in tourism domain. The system combines the content-based, collaborative, demographic and semantic
techniques in and implemented in a weighted and cascading recommendation formulation. Our preliminary work shows
that this hybrid approach can mitigate the weaknesses shown by these recommendation techniques when used
individually.
KEYWORDS
techniques and activities to carry out the development of an ontology. The concept mapping technique has been recently
used for developing ontologies related to different domains. However, the existing approaches using concept mapping do
not make use of any automatic term extraction process to ease the overall ontology development process. This paper
proposes a new approach which uses the concept mapping technique coupled with a Term Extraction Engine (TEE). The
engine automatically extracts the candidate terms from the competency questions which are later used for creating the
concept map. This concept map is later transformed in to a working ontology. The proposed approach reduces human
efforts and eases the ontology development process.
compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question
complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned. "
understandable web, also known as semantic web. In order to develop ontologies, several methodologies have been
proposed during the last two decades. Despite the fact, that quite a number of ontology engineering methodologies
have been proposed, still the field lacks widely accepted and mature methodologies. Most methodologies lack
sufficient details of techniques and activities employed in them. However, some methodologies provide sufficient
details including METHONTOLOGY. This article discusses and reports a critical analysis and comparison of these
methodologies. The analysis is performed based on a criterion, derived from related literature, trends and needs
which evolved over the years. The results of the analysis showed that there is no completely mature methodology.
Therefore, this research may act as a preliminary guide to come with a state of art ontology engineering
methodology, bridging up the existing gaps and shortfalls.
work we have focused on text fragment pattern learning through the fuzzy grammar method which
inputs include a predefined lexicon and text fragments that represents the expression of the grammar
class to be learned. However, the bottleneck of the success of the fuzzy grammar creation and in
common with other text learner often lies in the knowledge acquisition phase; due to the labour
intensive text annotation which also demands skills and background knowledge of the text. For this
reason, a semi-automated technique called automatic Terminal Grammar Recommender (TGR) is
devised to identify conceptually related lexicons in the texts and their related to create terminal
grammars by mining associations of words contexts. The approach recognizes that there is a degree of
local structure within such text and the technique exploits the local structure without the large
computational overhead of deeper analysis. Result from the comparison of the associative words
detected by TGR with the definition of a content category tool called General Inquirer on the data from
European Central Bank data is reported. Our findings show that our proposed method has managed to
reduce the manual effort of identifying conceptually similar lexicons to form terminal grammars. The
average of matched generated terminal grammar clusters compared to General Inquirer is 54.85%
which indicates that at least half the expensive effort to construct conceptually related lexicon is saved.
This hint the potential of word context association mining in automated conceptual lexicon generation.
madhab. Pilgrims can gain their knowledge about the
requirements of Umrah using books, expert and existent question
answering systems but still they suffer from the lack of
complexity and natural language patterns. This paper proposes
the semantic based question answering system to able pilgrims to
compose any question about Umrah in natural language format.
The proposed system used ontology to represent the knowledge
about ritual of Umrah and Pilgrims. The question complexity for
question in natural language is observed since it needs to be map
with the contents in the ontology. An Umrah Knowledge module
in this system covers all the rules and fact in the ontology format
and the Educational modules is responsible for question
answering interaction.
computer science a number of approaches for developing
ontologies have been proposed. Different approaches focus on
distinct aspects of the ontology development process and make
use of various techniques for developing ontologies. It is an
accepted fact that the ontology development process relies on
human feedback and decisions during various phases of
ontology development. However, most of the existing
approaches neglect this aspect of ontology development. In
order to bridge this gap, this paper proposes an ontology
development approach using the concept mapping technique,
which is human centered in nature. This approach eases the
overall ontology development process. It allows developing
ontologies which involve human feedback during the evolution
of the ontology design.
of research interest due to the rapid growth of social media
users. Despite the availability of a vast number of opinion
features and classification techniques, review classification still
remains a challenging task. In this work we applied stylometric
features, i.e. lexical and syntactic, using supervised machine
learning classifiers, i.e. Support Vector Machine (SVM) with
Sequential Minimal Optimization (SMO) and Naive Bayes,
to detect deceptive opinion. Detecting deceptive opinion by
a human reader is a difficult task because spammers try to
write wise reviews, therefore it causes changes in writing style
and verbal usage. Hence, considering the stylometric features
help to distinguish the spammer writing style to find deceptive
reviews. Experiments on an existing hotel review corpus suggest
that using stylometric features is a promising approach for
detecting deceptive opinions.
the recommendation system is the personalization which tailored information according to users’ needs and adaptation
which responds to users’ needs in a suitable manner as their preferences change. Numerous techniques like contentbased,
collaborative, demographic and semantic recommendation have already been proposed. Sometimes the
combination of these techniques called the hybrid recommendation is used for better results. Different strategies are used
to combine recommendation techniques in the hybrid recommendation method such as weighted, cascading and feature
augmented hybrid. This paper presents mobile software called Travel-Buddy, which will focus on personalized
recommendation in tourism domain. The system combines the content-based, collaborative, demographic and semantic
techniques in and implemented in a weighted and cascading recommendation formulation. Our preliminary work shows
that this hybrid approach can mitigate the weaknesses shown by these recommendation techniques when used
individually.
KEYWORDS
techniques and activities to carry out the development of an ontology. The concept mapping technique has been recently
used for developing ontologies related to different domains. However, the existing approaches using concept mapping do
not make use of any automatic term extraction process to ease the overall ontology development process. This paper
proposes a new approach which uses the concept mapping technique coupled with a Term Extraction Engine (TEE). The
engine automatically extracts the candidate terms from the competency questions which are later used for creating the
concept map. This concept map is later transformed in to a working ontology. The proposed approach reduces human
efforts and eases the ontology development process.
compatible ontology triple construction and semantic mapping. Existing studies have focused mainly on the semantic disambiguation such as through consolidation where user interaction is initiated so that relevant concept can be chosen by the user to be inserted into the SPARQL. In this paper we focus on the linguistic challenge in NLI, specifically on the question
complexity depth, processes that need to be performed to answer the question and gaps in existing study. It is concluded that more works are in demand to process complex questions such that involve multi-variables and multi-triples. Besides the issues posed by the answer generation for the combined sub-questions in the composite question, the challenges faced by the simple question is also inherited which requires an application that is robust in ontology concept annotation. This will ensure that the translated query would capture entirely the expression in the original question and accurate answer will be returned. "
understandable web, also known as semantic web. In order to develop ontologies, several methodologies have been
proposed during the last two decades. Despite the fact, that quite a number of ontology engineering methodologies
have been proposed, still the field lacks widely accepted and mature methodologies. Most methodologies lack
sufficient details of techniques and activities employed in them. However, some methodologies provide sufficient
details including METHONTOLOGY. This article discusses and reports a critical analysis and comparison of these
methodologies. The analysis is performed based on a criterion, derived from related literature, trends and needs
which evolved over the years. The results of the analysis showed that there is no completely mature methodology.
Therefore, this research may act as a preliminary guide to come with a state of art ontology engineering
methodology, bridging up the existing gaps and shortfalls.
work we have focused on text fragment pattern learning through the fuzzy grammar method which
inputs include a predefined lexicon and text fragments that represents the expression of the grammar
class to be learned. However, the bottleneck of the success of the fuzzy grammar creation and in
common with other text learner often lies in the knowledge acquisition phase; due to the labour
intensive text annotation which also demands skills and background knowledge of the text. For this
reason, a semi-automated technique called automatic Terminal Grammar Recommender (TGR) is
devised to identify conceptually related lexicons in the texts and their related to create terminal
grammars by mining associations of words contexts. The approach recognizes that there is a degree of
local structure within such text and the technique exploits the local structure without the large
computational overhead of deeper analysis. Result from the comparison of the associative words
detected by TGR with the definition of a content category tool called General Inquirer on the data from
European Central Bank data is reported. Our findings show that our proposed method has managed to
reduce the manual effort of identifying conceptually similar lexicons to form terminal grammars. The
average of matched generated terminal grammar clusters compared to General Inquirer is 54.85%
which indicates that at least half the expensive effort to construct conceptually related lexicon is saved.
This hint the potential of word context association mining in automated conceptual lexicon generation.