Insult Detection in Social Network Comments Using Possibilistic Based Fusion Approach

Ismail, Mohamed Maher Ben; Bchir, Ouiem

doi:10.1007/978-3-319-10509-3_2

Cited by 9 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ref. , the authors proposed a possibilistic‐based local approach that adapts the fusion method to different regions of the feature space. It categorizes the training samples into different clusters based on the subset of features used by the single classifiers and their confidences.…”

Section: Related Workmentioning

confidence: 99%

“…The possibilistic‐based context extraction for local fusion algorithm in Ref. has been formulated as partitioning the data into C clusters minimizing one objective function. However, this clustering approach requires the estimation of various parameters using complex optimization and is prone to several local minima.…”

Section: Local Fusion Based On Possibilistic Context Extractionmentioning

confidence: 99%

“…To overcome this potential drawback, we propose a semisupervised version of the algorithm in Ref. . The supervision information relies on two sets of pairwise constraints.…”

Section: Local Fusion Based On Possibilistic Context Extractionmentioning

confidence: 99%

“…More specifically, we modify the objective function in Ref. as follows:

\begin{matrix} true \\ right J & = & left \sum_{j = 1}^{N} \sum_{i = 1}^{C} u_{i j}^{m} \sum_{k = 1}^{K} v_{i k}^{q} d_{i j k}^{2} \\ left + \sum_{j = 1}^{N} \sum_{i = 1}^{C} β_{i} u_{i j}^{m} {(\sum_{k = 1}^{K} ω_{i k} y_{k j} - t_{j})}^{2} \\ left + \sum_{i = 1}^{C} η_{i} \sum_{j = 1}^{N} {(1 - u_{i j})}^{m} \\ left + μ ([] \sum_{({boldX}_{t}, {boldX}_{k} \in N L)} \sum_{i = 1}^{C} u_{t j}^{m} u_{k j}^{m} + \sum_{({boldX}_{t}, {boldX}_{k} \in S L)} \sum_{i = 1}^{C} \sum_{p = 1, p \neq i}^{C} u_{t j}^{m} u_{k j}^{m}), \end{matrix}

subject to

\sum_{i = 1}^{C} u_{i j} = 1 \forall j, u_{i j} \in [0, 1] \forall i, j,

\sum_{k = 1}^{K} v_{i k} = 1 \forall i, v_{i k} \in [...

…”

Section: Local Fusion Based On Possibilistic Context Extractionmentioning

confidence: 99%

“…To alleviate this problem, we include a semisupervised learning term in the proposed objective function. This categorization process associates a possibilistic membership, representing the degree of typicality, with each data sample to identify and reduce the influence of noise points and outliers . Also, an expert is appointed for each obtained cluster.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Semisupervised Local Fusion Approach for Mine Detection in SONAR Data

Ismail

Bchir

2015

Int. J. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel approach for automatic mine detection in SOund NAvigation and Ranging (SONAR) data. The proposed framework relies on possibilistic‐based fusion method to classify SONAR instances as mine or mine‐like object. The proposed semisupervised algorithm minimizes some objective function, which combines context identification, multi‐algorithm fusion criteria, and a semisupervised learning term. The optimization aims to learn contexts as compact clusters in subspaces of the high‐dimensional feature space via possibilistic semisupervised learning and feature discrimination. The semisupervised clustering component assigns degree of typicality to each data sample to identify and reduce the influence of noise points and outliers. Then, the approach yields optimal fusion parameters for each context. The experiments on synthetic data sets and standard SONAR data set show that our semisupervised local fusion outperforms individual classifiers and unsupervised local fusion.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Local Fusion Based On Possibilistic Context Extractionmentioning

confidence: 99%

“…To overcome this potential drawback, we propose a semisupervised version of the algorithm in Ref. . The supervision information relies on two sets of pairwise constraints.…”

Section: Local Fusion Based On Possibilistic Context Extractionmentioning

confidence: 99%

“…More specifically, we modify the objective function in Ref. as follows: