Examining Personalization in Academic Web Search

Salehi, Sara; Du, Jia Tina; Ashman, Helen

doi:10.1145/2700171.2791039

Cited by 15 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [4] a heavy reliance on search engines by academic users was found. This brought personalisation into the focus of research, prompting Salehi et al's [24] research into personalisation of search results in academia. Using alternative search setups involving Startpage and Tor to depersonalize search results and comparing the rank order of different search results using the percentage of result overlap and Hamming distance [24], it was found that on average only 53% of search results appear in both personalised and unpersonalised search.…”

Section: Related Studies On Search Results Comparisonmentioning

confidence: 99%

“…Unpersonalised search 2: This second condition attempted to completely depersonalise search query results through the use of the Startpage search engine running on Tor, and is borrowed directly from Salehi et al [24]. Startpage is a search engine that gathers the best Google results, but does not reveal or store any personal information of the user.…”

Section: Methodsmentioning

confidence: 99%

“…Startpage is a search engine that gathers the best Google results, but does not reveal or store any personal information of the user. It has also been awarded a European Privacy Seal [24]. Tor is essentially a modified Mozilla Firefox Browser with additional proxy applications and extensions that hides any identifying information by fragmenting the links between the client and server by redirecting the traffic through thousands of relays [11].…”

Section: Methodsmentioning

confidence: 99%

“…Mean response (SD) Frequency of use 4 (0.92) As the first point of enquiry 4 (0.91) Search engine comparison frequency 2 (1.05) Impact on quality of work 4 (0.90) That the overwhelming majority of participants use Google as their first point of enquiry at work draws comparisons with studies that found that around 80% of Internet users in an academic context used Google search as their first point of enquiry [4,24]. The participants in the study by Du et al [4] indicated that this was because they found Google easy to use, and that it had become a habit to use Google as the first option when they needed to search for information.…”

Section: Survey Itemmentioning

confidence: 99%

“…We based the research design of our experiment on the previous studies that sought to investigate search result personalisation in an academic search context [4,24] and the quantification of search result personalisation [10,22]. Additionally, we introduce search result relevance as an additional dimension.…”

Section: Research Design and Datamentioning

confidence: 99%

See 4 more Smart Citations

You Can’t See What You Can’t See: Experimental Evidence for How Much Relevant Information May Be Missed Due to Google’s Web Search Personalisation

Luczak‐Roesch

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The influence of Web search personalisation on professional knowledge work is an understudied area. Here we investigate how public sector officials self-assess their dependency on the Google Web search engine, whether they are aware of the potential impact of algorithmic biases on their ability to retrieve all relevant information, and how much relevant information may actually be missed due to Web search personalisation. We find that the majority of participants in our experimental study are neither aware that there is a potential problem nor do they have a strategy to mitigate the risk of missing relevant information when performing online searches. Most significantly, we provide empirical evidence that up to 20% of relevant information may be missed due to Web search personalisation. This work has significant implications for Web research by public sector professionals, who should be provided with training about the potential algorithmic biases that may affect their judgments and decision making, as well as clear guidelines how to minimise the risk of missing relevant information.

show abstract

Section: Related Studies On Search Results Comparisonmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Survey Itemmentioning

confidence: 99%

Section: Research Design and Datamentioning

confidence: 99%

See 3 more Smart Citations

You Can’t See What You Can’t See: Experimental Evidence for How Much Relevant Information May Be Missed Due to Google’s Web Search Personalisation

Luczak‐Roesch

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

What you see depends on where you sit: The effect of geographical location on web‐searching for systematic reviews: A case study

Cooper

Lorenc

Schauberger³

2021

Research Synthesis Methods

View full text Add to dashboard Cite

There is limited guidance on how to web‐search in systematic reviews and concern relates to the reproducibility of searches using search engines such as Google. The aim of this paper is to address one potential source of variation in Google searches: does the geographical location of a researcher affect Google search returns? Using a virtual private network, we ran the same web‐search for the medical technology Dasatinib in 12 different countries. Two researchers independently extracted the search returns by country organised by page rank. We compared: C1. any difference in the items returned by Google searches between countries and C2. any difference in the page rank of items returned between countries. Searches were undertaken on Monday September 28th 2020. From 12 countries, 43 items were identified. For C1: 19 items were common to all 12 countries. Twenty‐four items were missed by searches in some countries. This means that there were differences in search returns between countries. For C2: a randomised trial reported by Raddich et al was the first search return for all countries. All other items, common to all countries, varied in their page‐rank. We find that geographic location would appear to influence Google search returns based on the findings of this case study. The findings suggest that recording the location of the researcher undertaking web‐searching may now be an important factor to report alongside detail on steps taken to minimise personalisation of web‐searches covered by recent guidance. This finding also has implications for stopping‐rules.

show abstract

Color the Word: Leveraging Web Images for Machine Translation of Untranslatable Words

Sande

Larson

2022

MultiMedia Modeling

View full text Add to dashboard Cite

Automatic translation allows people around the globe to communicate with one another. However, state-of-the art machine translation is still unable to capture fine-grained meaning. This paper introduces the idea of using Web image selections in text-to-text translation, specifically for lacunae, which are words that do not have a translation in another language. We asked human professional translators to rank Google translate translations of lacunae in German and Dutch. We then compared that ranking with a ranking based on color histograms of Web image data of the words. We found there is viable potential in the idea of using images to address lacunae in the field of machine translation. We publicly release a dataset and our code for others to explore this potential. Finally, we provide an outlook on research directions that would allow this idea to be used in practice.

show abstract

Examining Personalization in Academic Web Search

Cited by 15 publications

References 15 publications

You Can’t See What You Can’t See: Experimental Evidence for How Much Relevant Information May Be Missed Due to Google’s Web Search Personalisation

You Can’t See What You Can’t See: Experimental Evidence for How Much Relevant Information May Be Missed Due to Google’s Web Search Personalisation

What you see depends on where you sit: The effect of geographical location on web‐searching for systematic reviews: A case study

Color the Word: Leveraging Web Images for Machine Translation of Untranslatable Words

Contact Info

Product

Resources

About