Novelty detection using local context analysis

Fernández, Ronald T.; Losada, David E.

doi:10.1145/1277741.1277878

Cited by 7 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the new report has a low matching vaule with topics that has been detected, it will be looked as a new topic. Otherwise it will be add to related clustering [22]. In early researches, Single Pass algorithm is mostly used because of simple calculation and fast computing speed.…”

Section: ) Topic Detection and Trackingmentioning

confidence: 99%

A survey of Internet public opinion mining

Guo

Shi

et al. 2014

2014 IEEE International Conference on Progress in Informatics and Computing

View full text Add to dashboard Cite

Nowadays Internet has become a major public opinion formation and diffusion platform. How to acquire the public hotspots and trends by collecting and analyzing the massive data on the Internet is an important research topic in public opinion analysis. In this paper, we firstly introduce the definition and framework of Internet public opinion mining, then focus on the comparison and analysis of key techniques used in different layers, and finally make a summary and outlook.

show abstract

Section: ) Topic Detection and Trackingmentioning

confidence: 99%

A survey of Internet public opinion mining

Guo

Shi

et al. 2014

2014 IEEE International Conference on Progress in Informatics and Computing

View full text Add to dashboard Cite

show abstract

“…Non-parametric methods do not rely on probabilistic distribution of the data. One example of nonparametric method is statistics which are based on ranks [32][33][34][35][36][37][38][39][40][41][42][43][44][45]. Other examples include histogram profiling [46], the k-nearest neighbour [47] and k-means [29].…”

Section: Deviation Detection In Textmentioning

confidence: 99%

“…It fails to perform well when the document is decomposed into sentences [37]. Other similarity measures which are based on distance computation such as shown in [36,40,42] are only applicable to the chosen text representation scheme.…”

Section: Deviation Detection In Textmentioning

confidence: 99%

Deviation detection in text using conceptual graph interchange format and error tolerance dissimilarity function

Kamaruddin

Hamdan

Bakar

et al. 2012

IDA

View full text Add to dashboard Cite

The rapid increase in the amount of textual data has brought forward a growing research interest towards mining text to detect deviations. Specialized methods for specific domains have emerged to satisfy various needs in discovering rare patterns in text. This paper focuses on a graph-based approach for text representation and presents a novel error tolerance dissimilarity algorithm for deviation detection. We resolve two non-trivial problems, i.e. semantic representation of text and the complexity of graph matching. We employ conceptual graphs interchange format (CGIF)-a knowledge representation formalism to capture the structure and semantics of sentences. We propose a novel error tolerance dissimilarity algorithm to detect deviations in the CGIFs. We evaluate our method in the context of analyzing real world financial statements for identifying deviating performance indicators. We show that our method performs better when compared with two related text based graph similarity measuring methods. Our proposed method has managed to identify deviating sentences and it strongly correlates with expert judgments. Furthermore, it offers error tolerance matching of CGIFs and retains a linear complexity with the increasing number of CGIFs.

show abstract

“…In [6], Local Context Analysis [13] was used to define a query-oriented vocabulary that was applied to drive novelty detection. This helps to avoid redundant sentences and it is particularly useful as a high precision mechanism.…”

Section: Related Workmentioning

confidence: 99%

Novelty as a form of contextual re-ranking

Fernández

Losada

2008

Proceedings of the Second International Symposium on Information Interaction in Context

Self Cite

View full text Add to dashboard Cite

Current Information Retrieval systems are often based on topicality. They estimate relevance by comparing the similarity between the user query and each document. These systems do not take into account important contextual information. More specifically, they do not often apply mechanisms to filter out redundant information. We interpret context here as the set of chunks of text from the ranked set of documents that the user has already seen. This is a valuable contextual information to guide the retrieval processes in a way that avoids redundancy. It is desirable that the ranking of results is composed by relevant but also novel material. This means that each document must provide to the user unseen information which is related to his need.In this work we study different novelty detection approaches that make good use of this contextual information. We show that these techniques can be applied effectively and efficiently at the sentence level.

show abstract

Novelty detection using local context analysis

Cited by 7 publications

References 3 publications

A survey of Internet public opinion mining

A survey of Internet public opinion mining

Deviation detection in text using conceptual graph interchange format and error tolerance dissimilarity function

Novelty as a form of contextual re-ranking

Contact Info

Product

Resources

About