An answer recommendation framework for an online cancer community forum

Health community forums are a kind of online platform to discuss various matters related to management of illness. People are increasingly searching for answers online, particularly when they are diagnosed with cancer like life-threatening diseases. People seek suggestions or advice through these platforms to make decisions during their treatments. However, locating the correct information or similar people is often a great challenge for them. In this scenario, this paper proposes an answer recommendation system in an online breast cancer community forum that provide guidance and valuable references to users while making decisions. The answer is the summary of already discussed topic in the forum, so that they do not need to go through all the answer posts which spans over multiple pages or initiate a thread once again. There are three phases for the answer recommendation system, including query similarity model to retrieve the past similar query, query-answer pair generation and answer recommendation. Query similarity model is employed by a Siamese network with Bi-LSTM architecture which could achieve an F1-score of 85.5%. Also, the paper shows the efficacy of transfer learning technique to generalize the model well in our breast cancer query-query pair data set. The query-answer pairs are generated by an extractive summarization technique that is based on an optimization algorithm. The effectiveness of the generated summary is evaluated based on a manually generated summary, and the result shows a ROUGE-1 score of 49%.

Abstractive Summarization of Text Document in Malayalam Language: Enhancing Attention Model using POS Tagging Feature

Over the last few years, researchers are showing huge interest in sentiment analysis and summarization of documents. The primary reason being that huge volumes of information are available in textual format and this data has proven helpful for real-world applications and challenges. The sentiment analysis of a document will help the user comprehend the content’s emotional intent. Abstractive summarization algorithms generate a condensed version of the text which can then be used to determine the emotion represented in the text using sentiment analysis. Recent research in abstractive summarization concentrate on neural network based models, rather than conjunctions based approaches, which might improve the overall efficiency. Neural network models like attention mechanism are tried out to handle complex works with promising results. The proposed work aims to present a novel framework that incorporates the part of speech tagging feature to the word embedding layer which is then used as the input to the attention mechanism. With POS feature being part of the input layer, this framework is capable of dealing with words containing contextual and morphological information. The relevance of POS tagging here is due to its strong reliance on the language’s syntactic, contextual, and morphological information. The three main elements in the work are pre-processing, POS tagging feature in the embedding phase, and the incorporation of it into the attention mechanism. The word embedding provides the semantic concept about the word, while the POS tags give an idea about how significant the words are in the context of the content, which corresponds to the syntactic information. The proposed work was carried out in Malayalam, one of the prominent Indian languages. A Widely used and accepted dataset from the English language was translated to Malayalam for conducting the experiments. The proposed framework gives a ROUGE score of 28, which outperformed the baseline models.

Extractive summarization of Malayalam documents using latent Dirichlet allocation: An experience

Automatic text summarization (ATS) extracts information from a source text and presents it to the user in a condensed form while preserving its primary content. Many text summarization approaches have been investigated in the literature for highly resourced languages. At the same time, ATS is a complicated and challenging task for under-resourced languages like Malayalam. The lack of a standard corpus and enough processing tools are challenges when it comes to language processing. In the absence of a standard corpus, we have developed a dataset consisting of Malayalam news articles. This article proposes an extractive topic modeling-based multi-document text summarization approach for Malayalam news documents. We first cluster the contents based on latent topics identified using the latent Dirichlet allocation topic modeling technique. Then by adopting vector space model, the topic vector and sentence vector of the given document are generated. According to the relevant status value, sentences are ranked between the document’s topic and sentence vectors. The summary obtained is optimized for non-redundancy. Evaluation results on Malayalam news articles show that the summary generated by the proposed method is closer to the human-generated summaries than the existing text summarization methods.

Deep learning based analysis of sentiment dynamics in online cancer community forums: An experience

Online health communities (OHC) provide various opportunities for patients with chronic or life-threatening illnesses, especially for cancer patients and survivors. A better understanding of the sentiment dynamics of patients in OHCs can help in the precise formulation of the needs during their treatment. The current study investigated the sentiment dynamics in patients' narratives in a Breast Cancer community group (Breastcancer.org) to identify the changes in emotions, thoughts, stress, and coping mechanisms while undergoing treatment options, particularly chemotherapy, radiation, and surgery. Sentiment dynamics of users' posts was performed using a deep learning model. A sentiment change analysis was performed to measure change in the satisfaction level of the users. The deep learning model BiLSTM with sentiment embedding features provided a better F1-score of 91.9%. Sentiment dynamics can assess the difference in satisfaction level the users acquire by interacting with other users in the forum. A comparison of the proposed model with existing models revealed the effectiveness of this methodology.

Gene regulatory network from microarray data of colon cancer patients using TSK-type recurrent neural fuzzy network

In this work we applied a TSK-type recurrent neural fuzzy approach to extract regulatory relationship among genes and reconstruct gene regulatory network from microarray data. The identified signature has captured the regulatory relationship among 27 differentially expressed genes from microarray dataset. We applied three different methods viz., feed forward neural fuzzy, modified genetic algorithm and recurrent neural fuzzy, on the same data set for the inference of GRNs and the results obtained are almost comparable. In all tested cases, TRNFN identified more biologically meaningful relations. We found that 87.8% of the total interactions extracted by TRNFN are correct in accordance with the biological knowledge. Our analysis resulted in 2 major outcomes. First, upregulated genes are regulated by more genes than downregulated genes. Second, tumor activators activate other tumor activators and suppress tumor suppressers strongly in the disease environment. These findings will help to elucidate the common molecular mechanism of colon cancer, and provide new insights into cancer diagnostics, prognostics and therapy.

Comparative advantages of novel algorithms using MSR threshold and MSR difference threshold for biclustering gene expression data

The goal of biclustering in gene expression data matrix is to find a submatrix such that the genes in the submatrix show highly correlated activities across all conditions in the submatrix. A measure called mean squared residue (MSR) is used to simultaneously evaluate the coherence of rows and columns within the submatrix. MSR difference is the incremental increase in MSR when a gene or condition is added to the bicluster. In this chapter, three biclustering algorithms using MSR threshold (MSRT) and MSR difference threshold (MSRDT) are experimented and compared. All these methods use seeds generated from K-Means clustering algorithm. Then these seeds are enlarged by adding more genes and conditions. The first algorithm makes use of MSRT alone. Both the second and third algorithms make use of MSRT and the newly introduced concept of MSRDT. Highly coherent biclusters are obtained using this concept. In the third algorithm, a different method is used to calculate the MSRDT. The results obtained on bench mark datasets prove that these algorithms are better than many of the metaheuristic algorithms.