Due to the large amounts of words usually present in documents, some of their appearances can complicate the classification process and make it less accurate. Accordingly, word representation methods have been employed to handle this issue through the use of a comparative study. In this study, we compare the effectiveness of both word embedding and TF-IDF weighting schema by applying four classifiers to assess the accuracy of the classification. To evaluate the effectiveness of our study, it was tested on the popular 20Newsgroup text document dataset. Following our experimentation, we found that using the TF-IDF method and ANN classifiers on the 20Newsgroup dataset greatly enhanced the text documents' classification compared against the use of word embedding and other classifiers.

With the abundance of reviews published on the Web about a given product, consumers are looking for ways to view major opinions that can be presented in a quick and succinct way. Reviews contain many different opinions, making the ability to show a diversified review summary that focus on coverage and diversity a major goal. Most review summarization work focuses on showing salient reviews as a summary which might ignore diversity in summaries. In this paper, we present a graph-based algorithm that is capable of producing extractive summaries that are both diversified from a sentiment point of view and topically well-covered. First, we use statistical measures to find topical words. Then we split the dataset based on the sentiment class of the reviews and perform the ranking on each sentiment graph. When compared with different baselines, our approach scores best in most ROUGE metrics. Specifically, our approach shows improvements of 3.9% in ROUGE-1 and 1.8% in ROUGE-L in comparison with the best competing baseline.

Graph-based approaches for multi-document summarization have been widely used to extract top sentences for a summary. Traditionally, the documents' cluster is modeled as a graph of the cluster's sentences only which might limit the ability of recognizing topically discriminative sentences in regard to other clusters. In this paper, we propose StarSum a star bipartite graph which models sentences and their topic signature phrases. The approach ensures sentence similarity and content importance from the graph structure. We extract sentences in an approach that guarantees diversity and coverage which are crucial for multi-document summarization. Regardless of the simplicity of the approach in ranking, a DUC experiment shows the effectiveness of StarSum compared to different baselines.

In a multi-document settings, graph-based extractive summarization approaches build a similarity graph out of sentences in each cluster of documents then use graph centrality approaches to measure the importance of sentences. The similarity is computed between each pair of sentences. However, it is not clear if such approach captures high-order relations among more than two sentences or can differentiate between descriptive sentences of the cluster in comparison with other clusters. In this paper, we propose to model sentences as hyperedges and words as vertices using a hypergraph and combine it with topic signatures to differentiate between descriptive sentences and non-descriptive sentences. To rank sentences, we propose a new random walk over hyperedges that will prefer descriptive sentences of the cluster when measuring their centrality scores. Our approach outperform a number of baseline in the DUC 2001 dataset using the ROUGE metric.

The massive growth of the micro-blogging service Twitter has shed the light on the challenging problem of summarizing a collection of large number of tweets. This paper attempts to extract topical key phrases that would represent topics in tweets. Due to the informality, noise, and short length of tweets, such research is nontrivial. We tackle such challenges with extensive preprocessing approach. Followed by, introduction of new features that improve topical key phrase extraction in Twitter. We start by proposing a novel unsupervised graph-based keyword ranking method, called NE-Rank, that considers word weights in addition to edge weights when calculating the ranking. Then we introduce a new approach of leveraging hash tags when extracting key phrases. We have conducted a set of experiments showing the potential of both approaches with 16% to 39% improvement for NE-Rank and 20% improvement for hash tag enhanced extraction.