The Role of Named Entities in Linking News Articles During Preservation

Khan, Muzammil; Rahman, Arif Ur; Ullah, Muhammad Muneeb; Naseem, Rashid

doi:10.1007/978-3-030-21005-2_5

Cited by 6 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another close problem is to find clusters of related news articles such that a cluster has a high internal coherence ( i.e ., having articles from the same topic or word distribution), but different from other clusters ( Bisandu, Prasad & Liman, 2018 ; Salih & Jacksi, 2020 ; Khan et al, 2018 ). While articles within the cluster might be candidate background to each other, the cluster size is big, and selecting specific articles from the cluster to present to the reader of a specific query article is again a challenging problem.…”

Section: Background Linking Problemmentioning

confidence: 99%

Unsupervised query reduction for efficient yet effective news background linking

Essam¹,

Elsayed²

2023

PeerJ Computer Science

View full text Add to dashboard Cite

In this article, we study efficient techniques to tackle the news background linking problem, in which an online reader seeks background knowledge about a given article to better understand its context. Recently, this problem attracted many researchers, especially in the Text Retrieval Conference (TREC) community. Surprisingly, the most effective method to date uses the entire input news article as a search query in an ad-hoc retrieval approach to retrieve the background links. In a scenario where the lookup for background links is performed online, this method becomes inefficient, especially if the search scope is big such as the Web, due to the relatively long generated query, which results in a long response time. In this work, we evaluate different unsupervised approaches for reducing the input news article to a much shorter, hence efficient, search query, while maintaining the retrieval effectiveness. We conducted several experiments using the Washington Post dataset, released specifically for the news background linking problem. Our results show that a simple statistical analysis of the article using a recent keyword extraction technique reaches an average of 6.2× speedup in query response time over the full article approach, with no significant difference in effectiveness. Moreover, we found that further reduction of the search terms can be achieved by eliminating relatively low TF-IDF values from the search queries, yielding even more efficient retrieval of 13.3× speedup, while still maintaining the retrieval effectiveness. This makes our approach more suitable for practical online scenarios. Our study is the first to address the efficiency of news background linking systems. We, therefore, release our source code to promote research in that direction.

show abstract

Section: Background Linking Problemmentioning

confidence: 99%

Unsupervised query reduction for efficient yet effective news background linking

Essam¹,

Elsayed²

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Initially, articles were extracted from three local English newspapers, namely, Dawn News, The Tribune and The News. The normalised articles are formatted into an XML form, which can represent the textual content of the article along with metadata like the name of the newspaper (source), date of publication, author name and so on [5,21]. The online newspapers were scrolled for news articles on different days without following a particular pattern for the news article collection.…”

Section: Linking Digital News Storiesmentioning

confidence: 99%

A content-based technique for linking dual language news articles in an archive

Khan

Rahman

Ahmad

et al. 2020

Journal of Information Science

Self Cite

View full text Add to dashboard Cite

To retrieve a specific news article from a vast archive containing multilingual news articles against a user query or based on similarity among news articles is a challenging task. The task becomes even further complicated when the archive contains articles from a low resourced and morphologically complex language like Urdu, along with English new articles. The article proposes a content-based (lexical) similarity measure, that is, Common Ratio Measure for Dual Language (CRMDL), for linking digital news articles published in various online news sources. The similarity measure links Urdu-to-English news articles during the preservation process using an Urdu-to-English lexicon. A literature review showed that an Urdu-to-English lexicon did not exist, and therefore, the first task was to build a lexicon from multiple sources. The proposed similarity measure, that is, CRMDL, is evaluated rigorously on different data sets, of varying sizes, to assess the effectiveness. The experimental results show that the proposed measure is feasible and effective for similarity computation between Urdu and English news articles, which can obtain, on average, 50% precision and 67% recall. The performance can be improved sufficiently by managing the limitations summarised in the study.

show abstract

“…Therefore, a Common Ratio Measure for Stories (CRMS) is introduced, which is based on the similar terms used in the English news articles except stop words for linking digital news stories during preservation. The CRMS algorithm pseudo-code, experimental results are discussed and compared with human judgment comprehensively (Khan et al , 2018a, b).…”

Section: Term-based Similarity Measurementioning

confidence: 99%

“…To introduced content-based techniques for linking news articles during the preservation process in the DNSA. Text processing based on text features, such as common ratio based on terms frequency (Khan et al , 2018a, b), named entities (Khan et al , 2018a, b), term position, headline terms, information credibility, similar terms distance, etc. (Khan, 2018).…”

Section: Linking Digital News Stories In Dnsamentioning

confidence: 99%

See 1 more Smart Citation

The role of news title for linking during preservation process in digital archives

Khan

Ahmad³

et al. 2020

LHT

Self Cite

View full text Add to dashboard Cite

PurposeThe World Wide Web has become an essential platform for a news publication, and it has become one of the primary sources of information dissemination in the past few years. Electronic media, i.e., television channels, magazines and newspapers, have started publishing news online. This online information is prompt to be disappeared because of short life-span and imperative to be archived for the long-term and future generations. This paper presents a content-based similarity measure based on the headings of the news articles for linking digital news stories published in various newspapers during the preservation process that helps to ensure future accessibility.Design/methodology/approachTo evaluate the accuracy and assess the effectiveness and worth of the proposed measure for linking news articles in Digital News Story Archive (DNSA), we adopted both, system-centric and user-centric (human judgment) evaluation over different datasets of news articles.FindingsThe proposed similarity measure is evaluated using different sizes of datasets, and the results are compared by both user-centric technique, i.e., expert judgment and system-centric techniques, i.e., cosine similarity measure, extended Jaccard measure and common ratio measure for stories (CRMS). The comparison helps to get a broader impact and can be helpful for generalization of the measure for different categories of news articles. Multiple experiments have conducted the findings of which showed that the measure presented viable results for national and international news, while best results for linking sports news articles during preservation based on headings.Originality/valueThe DNSA preserves a huge number of news articles from multiple news sources and to link with a vast collection, which encourages to introduce an efficient linking mechanism with few terms to manipulate. The CRMS is modified to deal with the headings of news articles as a part of the digital news stories preservation framework and comprehensively analysed.

show abstract

The Role of Named Entities in Linking News Articles During Preservation

Cited by 6 publications

References 14 publications

Unsupervised query reduction for efficient yet effective news background linking

Unsupervised query reduction for efficient yet effective news background linking

A content-based technique for linking dual language news articles in an archive

The role of news title for linking during preservation process in digital archives

Contact Info

Product

Resources

About