You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: content/en/ai-in-mental-health.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,4 +33,6 @@ As AI technology [continues to advance](/ai-in-mental-health/harmony-going-forwa
33
33
34
34
*[Harmony at Lifecourse seminar](/ai-in-mental-health/harmony-at-lifecourse-seminar/) - on 15 May 2024, Eoin McElroy and Bettina Moltrecht gave a seminar Harmony: A global platform for harmonisation, translation and cooperation in mental health research for the Melbourne Children’s LifeCourse Initiative seminar series.
35
35
*[Harmony at Methodscon Futures](/ai-in-mental-health/harmony-at-methodscon-futures/) - on 11 and 12 September 2024, Bettina Moltrecht and Thomas Wood presented Harmony at Methodscon Futures in Manchester
36
+
*[Harmony and TIDAL workshop](/ai-in-mental-health/harmony-and-tidal-workshop/) - a collaboration with another team on the Wellcome Trust Data Prize for Mental Health
37
+
* See other [news coverage](/ai-in-mental-health/news-coverage/).
Combining survey sources is fraught with challenges, from differing data quality to incompatible response scales. Addressing these issues head-on is key to successful data harmonisation.
133
+
Combining survey sources is fraught with challenges, from differing data quality to incompatible response scales. Addressing these issues head-on is key to [successful data harmonisation](/data-harmonisation/).
@@ -18,13 +22,15 @@ You might find this guide helpful: https://opensource.guide/how-to-contribute as
18
22
**1. Start small, think big:**
19
23
20
24
- Don't feel pressured to tackle the most complex issues right away. Look for smaller tasks that align with your skills and interests.
21
-
- These could be fixing typos in documentation, improving code readability, or adding simple features that haven't been prioritised yet.
25
+
- These could be fixing typos in documentation, improving code readability, or [adding simple features that haven't been prioritised yet](/open-source-for-social-science/what-features-would-you-like-to-see-in-harmony/).
22
26
- Remember, every contribution, no matter how small, adds value to the project.
23
27
28
+
You can try finding [projects on Kaggle](/open-source-for-social-science/kaggle/) as a place to get started.
29
+
24
30
**2. Find your niche:**
25
31
26
32
- Choose a project that aligns with your passions and expertise. This engagement will fuel your motivation and make the learning curve more enjoyable.
27
-
- Explore projects you already use and appreciate, or discover new ones that pique your curiosity.
33
+
- Explore projects you already use and appreciate, or discover new ones that pique your curiosity.
28
34
29
35
**3. Embrace the learning curve:**
30
36
@@ -35,6 +41,7 @@ You might find this guide helpful: https://opensource.guide/how-to-contribute as
35
41
**4. Embrace imperfection:**
36
42
37
43
- Your first contribution might not be perfect, and that's perfectly OK!
44
+
- Even if you struggle to [run the code](/open-source-for-social-science/running-harmony-in-your-browser-with-no-internet-connection/), your feedback on that is helpful as it lets us [troubleshoot the code base](/open-source-for-social-science/troubleshooting-harmony/) for the next joiner.
38
45
- The open source community values learning and collaboration. Experienced developers are often happy to provide feedback and guidance to help you improve.
39
46
- Be open to constructive criticism and use it as an opportunity to learn and refine your skills.
40
47
@@ -43,16 +50,17 @@ You might find this guide helpful: https://opensource.guide/how-to-contribute as
43
50
- Every contribution, no matter how small, is a victory. Take pride in your accomplishments and celebrate your progress.
44
51
- Each contribution builds your confidence and skills, paving the way for even greater contributions in the future.
45
52
46
-
**Remember:** Open source communities thrive on diversity and inclusivity. Your unique perspective and skills are valuable, so don't be afraid to share them with the world. Take that first step, start small, and watch your contributions grow alongside your confidence. Together, we can shape the future of open source, one contribution at a time!
53
+
**Remember:** Open source communities thrive on diversity and inclusivity. Your unique perspective and skills are valuable, so don't be afraid to share them with the world. Take that first step, start small, and watch your contributions grow alongside your confidence.
47
54
48
55
## Ideas for open source projects you can contribute to
49
56
50
-
***Harmony** - we are always on the lookout for anyone who can work on back end (API), front end, or NLP side of Harmony! https://github.com/harmonydata/harmony
57
+
*[Harmony](/open-source-for-social-science/contributing-to-harmony-nlp-project/) - we are always on the lookout for anyone who can work on the back end (API), front end, or NLP side of Harmony! https://github.com/harmonydata/harmony
51
58
*[spaCy](https://github.com/explosion/spaCy) - one of the best known NLP libraries
52
59
*[Country Named Entity Recognition](https://github.com/fastdatascience/country_named_entity_recognition) - a lightweight Python library for recognising country names in unstructured text and returning Pycountry objects. Very simple and a good library to start with on your open source journey `pip install country_named_entity_recognition`
53
60
*[Drug Named Entity Recognition](https://github.com/fastdatascience/drug_named_entity_recognition) - a lightweight Python library for recognising drug names in unstructured text `pip install drug-named-entity-recognition`
54
61
*[Fast Stylometry](https://github.com/fastdatascience/faststylometry) - a Python library for identifying the author of an unknown text (forensic stylometry). `pip install faststylometry`. [Read tutorial](https://fastdatascience.com/fast-stylometry-python-library/).
55
62
63
+
56
64
## How can I contribute to Harmony?
57
65
58
66
Read our [guide to contributing to Harmony](/contributing-to-harmony/).
@@ -64,7 +72,7 @@ Harmony is a powerful [data harmonisation tool](/data-harmonisation/) which uses
64
72
Harmony's back end is built in Python and the front end is in React. There is also an [R library](/harmony-r-notebook-r-markdown-example/). Whether you're a seasoned developer or a coding newbie, there's a place for you. You can:
65
73
66
74
*[Browse open issues and pull requests](https://github.com/harmonydata/harmony/issues) and find a challenge that sparks your interest and contribute your unique skills.
67
-
***Help maintain the existing code:** Fix bugs, improve documentation, and suggest optimizations.
75
+
***Help maintain the existing code:**[Fix bugs](/open-source-for-social-science/harmony-update-new-features-and-bug-fixes/), improve documentation, and suggest optimisations.
68
76
***Develop new features:** Take Harmony to the next level by proposing and implementing innovative solutions.
69
77
70
78
### 2. Work on the NLP models
@@ -79,12 +87,17 @@ The deeper we understand language, the better we can harmonise the world's resea
79
87
80
88
### 3. Publicise Harmony
81
89
82
-
Harmony's mission thrives on awareness and accessibility. You can be a champion for open data by:
90
+
Harmony's mission thrives on awareness and accessibility. Can you [champion the Harmony project online](/open-source-for-social-science/marketing-for-open-science/)?
83
91
84
92
***Writing blog posts and articles:** Share your experiences with Harmony and inspire others to join the cause.
85
93
***Creating tutorials and videos:** Make Harmony approachable for beginners and showcase its potential to a wider audience.
86
94
***Promoting Harmony as an open source project on social media:** Share the love on Twitter, Facebook, and beyond, using the hashtag #OpenSourceHarmony.
95
+
***Join Harmony's public events** - we have run a [hackathon](/open-source-for-social-science/hackathon/), an [online orientation session](/open-source-for-social-science/harmony-orientation-session/) and been active in [Pydata](/open-source-for-social-science/pydata-meetup/), [AI Camp](/psychology-ai-tool/aicamp-meetup/) and other events.
87
96
88
-
**Ready to join the Harmony open source project?** Head over to our GitHub repository at [https://github.com/harmonydata/harmony](https://github.com/harmonydata/harmony), explore the free web tool at [harmonydata.ac.uk/app](https://harmonydata.ac.uk/app), and dive into our documentation. We're waiting for you with open arms (and open-source code)!
97
+
**Ready to join the Harmony open source project?** Head over to our GitHub repository at [https://github.com/harmonydata/harmony](https://github.com/harmonydata/harmony), explore the free web tool at [harmonydata.ac.uk/app](https://harmonydata.ac.uk/app), and dive into our documentation.
98
+
99
+
You can also try working on the [Harmony R package](/open-source-for-social-science/harmony-r-package/) on [CRAN](/open-source-for-social-science/harmony-cran/) or try extending the [Harmony API](/open-source-for-social-science/harmony-api/).
89
100
90
101
**Bonus tip:** We also have a [Docker container](https://hub.docker.com/r/harmonydata/harmonyapi) available, making it even easier to get started with Harmony. Just check out our documentation for more details.
102
+
103
+
Together, we can shape the future of Harmony as an open source project and make it [more sustainable](/open-source-for-social-science/sustainability/) for the future.
Copy file name to clipboardExpand all lines: content/en/blog/data-harmonisation.md
+3-2Lines changed: 3 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -87,7 +87,7 @@ In summary, data harmonisation brings about significant improvements in the qual
87
87
88
88
7.**Diverse Data Sources**: Integrating data from diverse sources adds complexity due to varying formats, standards, and quality. Each source may have its unique characteristics and challenges that need to be addressed in the harmonisation process.
89
89
90
-
8.**Data Quality Concerns**: Ensuring the accuracy, consistency, and reliability of the harmonised data is crucial. This involves identifying and correcting errors in the data, which can be a significant hurdle, especially when dealing with large volumes of data from multiple sources.
90
+
8.**Data Quality Concerns**: Ensuring the accuracy, consistency, and reliability of the harmonised data is crucial. This involves identifying and correcting errors in the data, which can be a significant hurdle, especially when dealing with [large volumes of data from multiple sources](/data-harmonisation/combine-multiple-survey-sources-best-practices/).
91
91
92
92
Each of these challenges represents a significant aspect of the data harmonisation process, requiring careful planning, skilled resources, and often sophisticated technological solutions to overcome.
93
93
@@ -118,10 +118,11 @@ Let's explore this need further in various sectors:
118
118
119
119
9.**Telecommunications**: Telecom companies use data harmonisation to integrate customer data, usage patterns, and network data from various sources. This helps in improving network efficiency, customer service, and in developing new services.
120
120
121
-
These examples demonstrate the vast applicability and critical importance of data harmonisation in extracting meaningful insights, making informed decisions, and enhancing operational efficiency across different sectors.
121
+
These examples demonstrate the vast applicability and critical importance of data harmonisation in [extracting meaningful insights](/data-harmonisation/extract-process-data-from-questionnaires/), making informed decisions, and enhancing operational efficiency across different sectors.
122
122
123
123
124
124
## Data Harmonisation in Practice
125
+
125
126
Data harmonisation is not a theoretical concept but a practical necessity across various sectors. For instance, in healthcare, harmonising patient data from different hospitals leads to better patient care and research outcomes. In [marketing](/data-harmonisation/data-harmonisation-for-marketing-success-strategies-and-insights/), it helps in understanding consumer behavior by integrating data from diverse sources.
126
127
127
128
**[Harmony: A Specialised Tool for Data Harmonisation](https://harmonydata.ac.uk/)**
Copy file name to clipboardExpand all lines: content/en/blog/extract-process-data.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -23,7 +23,9 @@ Let's go through these strategies together. Get ready to turn challenges into ch
23
23
24
24
Pulling [data from questionnaires](/data-harmonisation/find-matching-and-common-items-in-questionnaires-and-surveys/) is an important step in transforming the gathered responses into actionable insights. This involves handling both structured and unstructured data.
25
25
26
-
What’s the difference, you ask? Structured data is the kind that fits neatly into categories, such as the choices selected in a multiple-choice question. On the flip side, unstructured data includes the free-text responses where participants express their thoughts in their own words.
26
+
### Structured vs unstructured data
27
+
28
+
Structured data is the kind that fits neatly into categories, such as the choices selected in a multiple-choice question. On the flip side, unstructured data includes the free-text responses where participants express their thoughts in their own words.
27
29
28
30
Data can be collected in several ways – these ways each reflect the unique methods by which questionnaires are shared and completed. For instance, paper forms are a classic approach that requires participants to mark their answers physically. These responses then need to be manually keyed into a digital system for analysis – a process that might take a bit of elbow grease but is key for some research types.
29
31
@@ -59,7 +61,7 @@ Why bother with all this? Well, just like you wouldn't want to base your decisio
59
61
60
62
Seems like a lot of work? A customised method can greatly ease and improve the process. This is where we want to tell you about our favourite (and very own) tool: Harmony.
61
63
62
-
Harmony revolutionises the way we approach the complex task of harmonising questionnaire data. With its advanced Natural Language Processing (NLP) at the core, Harmony offers a tailored solution that excels in interpreting, comparing, and integrating data across languages and formats, making it invaluable for international research and projects with diverse data sources.
64
+
Harmony revolutionises the way we approach the complex task of [harmonising questionnaire data](/data-harmonisation/). With its advanced Natural Language Processing (NLP) at the core, Harmony offers a tailored solution that excels in interpreting, comparing, and integrating data across languages and formats, making it invaluable for international research and projects with diverse data sources.
@@ -20,3 +24,5 @@ If you want to upload multiple questionnaires in a single file, you can use Exce
20
24
In all cases we recommend clearly supplying question numbers, question texts, and removing extraneous information such as copyright disclaimers for best results.
21
25
22
26
If you are having trouble parsing a document in Harmony, you can [raise an issue](https://github.com/harmonydata/harmony/issues) or [try our troubleshooting tips](/troubleshooting-harmony).
27
+
28
+
Harmony is an [open source tool for social science research](/open-source-for-social-science/).
We are excited to announce that Harmony, a Natural Language Processing tool for data harmonisation, is now available on the Comprehensive R Archive Network [CRAN](https://cran.r-project.org/)!
15
+
We are excited to announce that Harmony, an [open source](/open-source-for-social-science/) Natural Language Processing tool for data harmonisation, is now available on the Comprehensive R Archive Network [CRAN](https://cran.r-project.org/)!
12
16
13
17
Previously, [Harmony R](/harmony-r-released/) could be installed using [devtools](https://www.r-project.org/nosvn/pandoc/devtools.html).
We have developed the R package for Harmony. To get started, you need R installed on your system.
13
+
We have developed the R package for Harmony and [open sourced](/open-source-for-social-science/) it. To get started, you need R installed on your system.
10
14
11
15
[Click here](https://colab.research.google.com/github/harmonydata/experiments/blob/main/Harmony_R_example.ipynb) to try an example in Google Colab.
0 commit comments