Data reuse and the open data citation advantage

Relationship between data availability and citation

Data reuse patterns from accession number attribution

A second, independent dataset was collected to correlate with reuse attributions made through mentions of accession numbers rather than formal citations.

Data and script availability

Statistical analyses were last run on Wednesday, April 3, 2013 with R version 2.15.1 (2012-06-22). Packages used included reshape2 (Wickham, 2007), plyr (Wickham, 2011), rms (Harrell, 2012), polycor (Fox, 2010), ascii (Hajage, 2011), ggplot2 (Wickham, 2009), gplots (Warnes et al., 2012), knitr (Xie, 2012), and knitcitations (Boettiger, 2013). P-values were two-tailed.

Raw data and statistical scripts are available in the Dryad data repository at http://doi.org/10.5061/dryad.781pv. Data collection scripts are on GitHub at https://github.com/hpiwowar/georeuse and https://github.com/hpiwowar/pypub.

The Markdown version of this manuscript with interleaved statistical scripts (Xie, 2012) is on GitHub https://github.com/hpiwowar/citation11k. Publication references are available in a publicly-available Mendeley group to facilitate exploration at http://www.mendeley.com/groups/2223913/11k-citation/papers/.

Description of cohort

We identified 10,557 articles published between 2001 and 2009 as collecting gene expression microarray data. Publicly available datasets in GEO or ArrayExpress had been found for 2,617 of these articles (25%, 95% confidence interval 24% to 26%). The papers were published in 667 journals, with the top 12 journals accounting for 30% of the papers (Table 2). Microarray papers were published more frequently in later years: 2% of articles in our sample were published in 2001, compared to 15% in 2009 (Table 3). The papers were cited between 0 and 2,643 times, with an average of 32 citations per paper and a median of 16 citations.

Data availability is associated with citation benefit

Without accounting for any confounding factors, the distribution of citations was similar for papers with and without archived data. That said, we hasten to mention several strong confounding factors. For example, the number of citations a paper has received is strongly correlated to the date it was published: older papers have had more time to accumulate citations. Furthermore, the probability of data archiving is also correlated with the age of an article – more recent articles are more likely to archive data (Piwowar, 2011a). Accounting for publication date, the distribution of citations for papers with available data is right-shifted relative to the distribution for those without, as seen in Fig. 1.

Other variables have been shown to correlate with citation rate (Fu & Aliferis, 2008). Because single-variable correlations can be misleading, we performed multivariate regression to isolate the relationship between data availability and citation rate from confounders.

The multivariate regression included attributes representing an article’s journal, journal impact factor, date of publication, number of authors, number of previous citations of the first and last author, number of previous publications of the last author, whether the paper was about animals or plants, and whether the data was made publicly available. Citations were 9% higher for papers with available data, independent of other variables (p < 0.01, 95% confidence intervals [5% to 13%]).

We also analyzed a subset of manually curated articles. The findings were similar to those of the whole sample, supporting our assumption that errors in automated inclusion criteria determination did substantially influence the estimate (see Article S1).

More covariates led to a more conservative estimate

Our estimate of citation benefit, 9% as per the multivariate regression, is notably smaller than the 69% (95% confidence intervals of 18% to 143%) citation advantage found by Piwowar, Day & Fridsma (2007), even though both studies examined publicly available gene expression microarray data. There are several possible reasons for this difference.

First, Piwowar, Day & Fridsma (2007) concentrated on datasets from high-impact studies: human cancer microarray trials published in the early years of microarray analysis (between 1999 and 2003). By contrast, the current study included gene expression microarray data studies on any subject published between 2001 and 2009. Second, because the Piwowar, Day & Fridsma (2007) sample was small (85 papers), the previous analysis included only a few covariates: publication date, journal impact factor, and country of the corresponding author.

We attempted to reproduce the Piwowar, Day & Fridsma (2007) methods with the current sample. Limiting the inclusion criteria to studies with MeSH terms “human” and “cancer”, and to papers published between 2001 and 2003, reduced the cohort to 308 papers. Running this subsample with the covariates used in the Piwowar, Day & Fridsma (2007) paper resulted in a comparable estimate to the 2007 paper: a citation increase of 47% (95% confidence intervals of 6% to 103%).

The subsample of 308 papers was large enough to include a few additional covariates: number of authors and citation history of the last author. Including these important covariates decreased the estimated effect to 18% with a confidence interval that spanned a loss of 17% citations to a benefit of 66%.

Citation benefit over time

After completing our comparison to prior results, we returned to the whole sample. Because publication date is such a strong correlate with both citation rate and data availability, we ran regressions for each publication year individually. The estimate of citation benefit varied by year of publication. The citation benefit was greatest for data published in 2004 and 2005, at about 30%. Earlier years showed citation benefits with wider confidence intervals due to relatively small sample sizes, while more recently published data showed a less pronounced citation benefit (Fig. 2).

Data reuse is a demonstrable component of citation benefit

To estimate the proportion of the citation benefit directly attributable to data reuse, we randomly selected and manually reviewed 138 citations. We classified eight (6%) of the citations as attributions for data reuse (95% CI: 3% to 11%).

Evidence of reuse from mention of dataset identifiers in full text

A complementary dataset was collected and analyzed to characterize data reuse: direct mention of dataset accession numbers in the full text of papers. In total there were 9274 mentions of GEO datasets in papers published between 2000 and 2010 within PubMed Central across 4543 papers written by author teams whose last names did not match the names of those who deposited the data. Extrapolating this to all of PubMed, we estimated there may be about 1.4081 × 104 third-party reuses of GEO data attributed through accession numbers in all of PubMed for papers published between 2000 and 2010.

The number of reuse papers started to grow rapidly several years after data archiving rate started to grow. In recent years both the number of datasets and the number of reuse papers have been growing rapidly, at about the same rate, as shown in Fig. 3. The level of third-party data use was high: for 100 datasets deposited in year 0, we estimate that 40 papers in PubMed reused a dataset by year 2, 100 by year 4, and more than 150 by year 5. This data reuse curve is remarkably constant for data deposited between 2004 and 2009. The reuse growth trend for data deposited in 2003 has been slower, perhaps because 2003 data is not as ground-breaking as earlier data, and probably not as standards-compliant and technically relevant as later data.

We found that most instances of self-reuse (identified by surname overlap with data submission record) were published within two years of dataset publication. This pattern contrasts sharply with third party data reuse, as shown in Fig. 4. The cumulative number of third-party reuse papers is illustrated in Fig. 5; separate lines are displayed for different dataset publication years.

Because the number of datasets published has grown dramatically with time, it is instructive to consider the cumulative number of third-party reuses normalized by the number of datasets deposited each year (Fig. S1). In the earliest years for which data is available, 2001–2002, there were relatively few data deposits, but these datasets have been disproportionately reused. We excluded the early years from the plot to examine the pattern of data reuse once gene expression datasets became more common. Since 2003, the rate at which individual datasets were reused increased with each year of data publication.

Growth in the number of datasets in each reuse paper over time

The number of distinct datasets used in a reuse paper was found to increase over time (Fig. 6). From 2002 to 2004 almost all reuse papers only used one or two datasets. By 2010, 25% of reuse papers used 3 or more datasets.

Distribution of reuse across datasets

It is useful to know the distribution of reuse amongst datasets. Because our methods only detect reuse by papers in PubMed Central (a small proportion of the biomedical literature) and only when the accession number is given in the full text, our estimates of reuse are extremely conservative. Despite this, we found that reuse was not limited to only a few papers (Fig. 7). Nearly all datasets published in 2001 were reused at least once. The proportion of reused datasets declined in subsequent years, with a plateau of about 20% for data deposited between 2003 and 2007. The actual rate of reuse across all methods of attribution, and extrapolated to all of PubMed, is probably much higher.

Distribution of the age of reused data

We found the authors of third-party data reuse papers were most likely to use data that was 3–6 years old by the time their paper was published, normalized for how many datasets were deposited each year (Fig. 8). For example, in aggregate, microarray reuse papers from 2005 mentioned the accession numbers of more than 5% of all datasets that had been submitted two years earlier, in 2003. Reuse papers from 2008 mentioned about 7% of the datasets submitted two years earlier (in 2006), more than 10% of the datasets submitted 3 and 4 years previously (2005 and 2004), and about 7% of the datasets submitted 5 years earlier, in 2003.

The open data citation benefit

One of the primary findings of this analysis is that papers with publicly available microarray data received more citations than similar papers that did not make their data available, even after controlling for many variables known to influence citation rate. We found the open data citation benefit for this sample to be 9% overall (95% confidence interval: 5% to 13%), but the benefit depended heavily on the year the dataset was made available. Datasets deposited very recently have so far received no (or few) additional citations, while those deposited in 2004–2005 showed a clear benefit of about 30% (confidence intervals 15% to 48%). Older datasets also appeared to receive a citation benefit, but the estimate is less precise because relatively little microarray data was collected or archived in the early 2000s.

The citation benefit reported here is smaller than that reported in the previous study by Piwowar, Day & Fridsma (2007), which estimated a citation benefit of 69% for human cancer gene expression microarray studies published before 2003 (95% confidence intervals of 18% to 143%). Our attempt to replicate the Piwowar, Day & Fridsma (2007) study here suggests that aspects of both the data and analysis can help to explain the quantitatively different results. It appears that clinically relevant datasets released early in the history of microarray analysis had a particularly strong impact. Importantly, however, the new analysis also suggested that the previous estimate was confounded by significant citation correlates, including the total number of authors and the citation history of the last author. This finding reinforces the importance of accounting for covariates through multivariate analysis and the need for large samples to support full analysis: the 69% estimate is probably too high, even for its high-impact sample. Nonetheless, a 10%–30% is citation benefit may still be an effective motivator for data deposit, given that prestigious journals have been known to advertise their impact factors to three decimal places (Smith, 2006).

A paper with open data may be cited for reasons other than data reuse, and open data may be reused without citation of the original paper. Ideally, we would like to separate these two phenomena (data reuse and paper citation) and measure how often the latter is driven by the former. In our manual analysis of 138 citations to papers with open data, we observed that 6% (95% CI: 3% to 11%) of citations were in the context of data reuse. Although this methodology and the sample size do not allow us to estimate with any precision the proportion of the citation benefit attributable to data reuse, the result is consistent with data reuse being a major contributor.

Another important result of the citation analysis is that the number of papers based on self data reuse declined steeply after two years, while data reuse papers by third-party authors continued to accumulate even after six years. This finding suggests that although researchers may have some incentive for protecting their own exclusive use of data close to the time of the initial publication, the equation changes dramatically after a short period. This finding provides some evidence to guide policy decisions regarding the length of data embargoes allowed by journal archiving policies such as the Joint Data Archiving Policy described by Rausher et al. (2010).

While we cannot generalize from these detailed patterns of data reuse and citation to other datatypes or domains, the cumulative citation benefit seems to be quantitatively similar in a number of different fields (Gleditsch, Metelits & Strand, 2003; Piwowar, Day & Fridsma, 2007; Ioannidis et al., 2009; Pienta, Alter & Lyle, 2010; Henneken & Accomazzi, 2011; Sears, 2011; Dorch, 2012).

Challenges collecting citation data

This study required obtaining citation counts for thousands of articles using PubMed IDs. This process was not supported at the time of data collection using either Thomson Reuter’s Web of Science or Google Scholar. Although this type of query was supported by Elsevier’s Scopus database, we lacked institutional access to Scopus, individual subscriptions were not available, and attempts to request access through Scopus staff were unsuccessful. One of us (HP) attempted to use the British Library’s walk-in access of Scopus while visiting the UK. Unfortunately, the British Library’s policies did not permit any method of electronic input of the PubMed identifier list (the list is 10,000 elements long). HP eventually obtained official access to Scopus through a Research Worker agreement with Canada’s National Research Library (NRC-CISTI), after being fingerprinted to obtain a police clearance certificate because she had recently lived in the United States.

Our understanding of research practice suffers because access to tools and data is so difficult.

Patterns of data reuse

To better understand patterns of data reuse, a larger sample of reuse instances was needed than could easily be assembled through manual classification of citation context. To that end, we used a complementary source of information about reuse of the same datasets: direct mention of GEO or ArrayExpress accession numbers within the body of a full-text research article. The large number of instances of reuse identified this way allowed us to ask questions about the distribution of reuse over time and across datasets. The results indicate that dataset reuse has been increasing over time (excluding the initial years of GEO and ArrayExpress when few datasets were deposited and reuse appears to have been atypically broad). Recent reuse analyses include more datasets, on average, than older reuse studies. Also, the fact that reuse was greatest for datasets published between three and six years previously suggests that the lower citation benefit we observed for recent papers is due, at least in part, to a relatively short follow-up time.

Extrapolating to all of PubMed, we estimate the number of reuse papers published per year is on the same order of magnitude – and likely greater – than the number of datasets made available. This data reuse curve is remarkably constant for data deposited between 2004 and 2009. This finding reinforces the conclusions of an earlier analysis: even modest data reuse can provide an impressive return on investment for science funders (Piwowar, Vision & Whitlock, 2011b).

Finally, we observed a moderate proportion of datasets being reused by third parties (more than 20% of the datasets deposited between 2003 and 2007). It is important to recognize that this is likely a gross underestimate. It includes only those instances of reuse that can be recognized through the mention of accession number in PubMed Central. No attempt has been made to extrapolate these distribution statistics to all of PubMed, nor to identify additional attributions through paper citations or mentions of the archive name alone. Further, many important instances of data reuse leave no trace in the published literature, such as those in education and training.

Reasons for the data citation benefit

While we cannot exclude that the open data citation benefit is driven entirely by third-party data reuse, there may be other factors contributing to the effect either directly or indirectly. The literature that has considered the possibility of an Open Access citation benefit (e.g., Craig et al., 2007) indicates a number of other factors that may also be relevant to open data. Building upon this work, we suggest several possible sources for an “Open Data citation benefit”:

1. Data Reuse. Papers with available datasets can be used in ways that papers without data cannot, and may receive additional citations as a result.

2. Credibility Signalling. The credibility of research findings may be higher for research papers with available data. Such papers may be preferentially chosen as background citations or the foundation of additional research.

3. Increased Visibility. Third party researchers may be more likely to encounter a paper with available data, either by a direct link from the data or indirectly through cross-promotion. For example, links from a data repository to a paper may increase the search ranking of the research paper.

4. Early View. When data is made available before a paper is published, some citations may accrue earlier than they would otherwise because of accelerated awareness of the methods, findings, and so on.

5. Selection Bias. Authors may be more likely to publish data for papers they judge to be their best quality work, because they are particularly proud or confident of the results (Wicherts, Bakker & Molenaar, 2011).

The citation benefit observed in the current study is consistent with data reuse found in this study and the small-scale annotation reported in Rung & Brazma (2013). Nonetheless, it is possible some of the other sources suggested above may have contributed citations for the studies with available data. Further work will be needed to understand the relative contributions from each source. For example, in-depth analyses of all publications from a set of data-collecting authors could support measurement of selection bias. Observing search behavior of researchers, and the returned search hit results, could characterize increased visibility because of data availability. Hypothetical examples could be provided to authors to determine whether they would be systematically more likely to cite a paper with available data in situations in which they are considering the credibility of research findings.

Future work

Future work could improve on these results by considering and integrating all methods of data use attribution. This holistic effort would include identifying citations to the paper that describes the data collection, mentions of the dataset identifier itself – whether in full text, the references section, or supplementary information – citations to the dataset as a first-class research object, and even mentions of the data collection investigators in acknowledgement sections. The citations and mentions would need classification based on context to ensure they are in the context of data reuse.

The obstacles encountered in obtaining the citation data needed for this study, as described earlier in the Discussion, demonstrate that improvements in tools and practice are needed to make impact tracking easier and more accurate, for day-to-day analyses as well as studies for evidence-based policy. Such research is hamstrung without programmatic access to the full-text of the research literature and to the citation databases that underpin impact assessment. The lack of conventions and tool support for data attribution (Mooney & Newton, 2012) is also a significant obstacle, undoubtedly leading to undercounting in the present study. There is much room for improvement, and we are hopeful about recent steps toward data citation standards taken by initiatives such as DataCite.

Data from current and future studies could begin to be used to estimate the impact of policy decisions. For example, do embargo periods decrease the level of data reuse? Do restrictive or poorly articulated licensing terms decrease data reuse? Which types of data reuse are facilitated by robust data standards and which types are unaffected?

Qualitative assessment of data reuse is an essential complement to large-scale quantitative analyses. Repeating and extending previous studies will help develop an understanding of the potential of data reuse, areas of progress, and remaining challenges (e.g., Zimmerman, 2003; Wan & Pavlidis, 2007; Wynholds et al., 2012; Rolland & Lee, 2013). Usage statistics from primary data repositories and value-added repositories are also useful sources of insight into reuse patterns (Rung & Brazma, 2013).

Citations are blind to many important types of data reuse. The impact of data on practitioners, educators, data journalists, and industry researchers is not captured by attribution patterns in the scientific literature. Altmetrics indicators reveal discussions in social social media, syllabi, patents, and theses: analyzing such indicators for datasets would provide valuable evidence of reuse beyond the scientific literature. As evaluators move away from assessing research based on journal impact factor and toward article-level metrics, post-publication metrics rates will become increasingly important indicators of research impact (Piwowar, 2013).